Yoon Kim


2024

pdf bib
LangNav: Language as a Perceptual Representation for Navigation
Bowen Pan | Rameswar Panda | SouYoung Jin | Rogerio Feris | Aude Oliva | Phillip Isola | Yoon Kim
Findings of the Association for Computational Linguistics: NAACL 2024

We explore the use of language as a perceptual representation for vision-and-language navigation (VLN), with a focus on low-data settings. Our approach uses off-the-shelf vision systems for image captioning and object detection to convert an agent’s egocentric panoramic view at each time step into natural language descriptions. We then finetune a pretrained language model to select an action, based on the current view and the trajectory history, that would best fulfill the navigation instructions. In contrast to the standard setup which adapts a pretrained language model to work directly with continuous visual features from pretrained vision models, our approach instead uses (discrete) language as the perceptual representation. We explore several use cases of our language-based navigation (LangNav) approach on the R2R VLN benchmark: generating synthetic trajectories from a prompted language model (GPT-4) with which to finetune a smaller language model; domain transfer where we transfer a policy learned on one simulated environment (ALFRED) to another (more realistic) environment (R2R); and combining both vision- and language-based representations for VLN. Our approach is found to improve upon baselines that rely on visual features in settings where only a few expert trajectories (10-100) are available, demonstrating the potential of language as a perceptual representation for navigation.

pdf bib
Natural Language Embedded Programs for Hybrid Language Symbolic Reasoning
Tianhua Zhang | Jiaxin Ge | Hongyin Luo | Yung-Sung Chuang | Mingye Gao | Yuan Gong | Yoon Kim | Xixin Wu | Helen Meng | James Glass
Findings of the Association for Computational Linguistics: NAACL 2024

How can we perform computations over natural language representations to solve tasks that require symbolic and numeric reasoning? We propose natural language embedded programs (NLEP) as a unifying framework for addressing math/symbolic reasoning, natural language understanding, and instruction following tasks. Our approach prompts a language model to generate full Python programs that define functions over data structures which contain natural language representations of structured knowledge. A Python interpreter then executes the generated code and prints the output. Despite using a task-general prompt, we find that this approach can improve upon strong baselines across a range of different tasks including math and symbolic reasoning, text classification, question answering, and instruction following. We found that the generated programs are interpretable since they outline the exact reasoning process followed by the program interpreter.

pdf bib
Can You Learn Semantics Through Next-Word Prediction? The Case of Entailment
William Merrill | Zhaofeng Wu | Norihito Naka | Yoon Kim | Tal Linzen
Findings of the Association for Computational Linguistics ACL 2024

Do LMs infer the semantics of text from co-occurrence patterns in their training data? Merrill et al. (2022) argue that, in theory, sentence co-occurrence probabilities predicted by an optimal LM should reflect the entailment relationship of the constituent sentences, but it is unclear whether probabilities predicted by neural LMs encode entailment in this way because of strong assumptions made by Merrill et al. (namely, that humans always avoid redundancy). In this work, we investigate whether their theory can be used to decode entailment relations from neural LMs. We find that a test similar to theirs can decode entailment relations between natural sentences, well above random chance, though not perfectly, across many datasets and LMs. This suggests LMs implicitly model aspects of semantics to predict semantic effects on sentence co-occurrence patterns. However, we find the test that predicts entailment in practice works in the opposite direction to the theoretical test. We thus revisit the assumptions underlying the original test, finding its derivation did not adequately account for redundancy in human-written text. We argue that better accounting for redundancy related to *explanations* might derive the observed flipped test and, more generally, improve computational models of speakers in linguistics.

pdf bib
CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs’ Mathematical Reasoning Capabilities
Yujun Mao | Yoon Kim | Yilun Zhou
Findings of the Association for Computational Linguistics ACL 2024

Recent large language models (LLMs) have shown indications of mathematical reasoning ability on challenging competition-level problems, especially with self-generated verbalizations of intermediate reasoning steps (i.e., chain-of-thought prompting). However, current evaluations mainly focus on the end-to-end final answer correctness, and it is unclear whether LLMs can make use of helpful side information such as problem-specific hints. In this paper, we propose a challenging benchmark dataset for enabling such analyses. The Concept and Hint-Annotated Math Problems (CHAMP) consists of high school math competition problems, annotated with concepts, or general math facts, and hints, or problem-specific tricks. These annotations allow us to explore the effects of additional information, such as relevant hints, misleading concepts, or related problems. This benchmark is difficult, with the best model only scoring 58.1% in standard settings. With concepts and hints, performance sometimes improves, indicating that some models can make use of such side information. Furthermore, we annotate model-generated solutions for their correctness. Using this corpus, we find that models often arrive at the correct final answer through wrong reasoning steps. In addition, we test whether models are able to verify these solutions, and find that most models struggle.

pdf bib
Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks
Zhaofeng Wu | Linlu Qiu | Alexis Ross | Ekin Akyürek | Boyuan Chen | Bailin Wang | Najoung Kim | Jacob Andreas | Yoon Kim
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)

The impressive performance of recent language models across a wide range of tasks suggests that they possess a degree of abstract reasoning skills. Are these skills general and transferable, or specialized to specific tasks seen during pretraining? To disentangle these effects, we propose an evaluation framework based on “counterfactual” task variants that deviate from the default assumptions underlying standard tasks. Across a suite of 11 tasks, we observe nontrivial performance on the counterfactual variants, but nevertheless find that performance substantially and consistently degrades compared to the default conditions. This suggests that while current LMs may possess abstract task-solving skills to an extent, they often also rely on narrow, non-transferable procedures for task-solving. These results motivate a more careful interpretation of language model performance that teases apart these aspects.

pdf bib
Paraphrase and Solve: Exploring and Exploiting the Impact of Surface Form on Mathematical Reasoning in Large Language Models
Yue Zhou | Yada Zhu | Diego Antognini | Yoon Kim | Yang Zhang
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)

This paper studies the relationship between the surface form of a mathematical problem and its solvability by large language models. We find that subtle alterations in the surface form can significantly impact the answer distribution and the solve rate, exposing the language model’s lack of robustness and sensitivity to the surface form in reasoning through complex problems. To improve mathematical reasoning performance, we propose Self-Consistency-over-Paraphrases (SCoP), which diversifies reasoning paths from specific surface forms of the problem. We evaluate our approach on four mathematics reasoning benchmarks over three large language models and show that SCoP improves mathematical reasoning performance over vanilla self-consistency, particularly for problems initially deemed unsolvable. Finally, we provide additional experiments and discussion regarding problem difficulty and surface forms, including cross-model difficulty agreement and paraphrasing transferability, and Variance of Variations (VOV) for language model evaluation.

pdf bib
What Do Language Models Hear? Probing for Auditory Representations in Language Models
Jerry Ngo | Yoon Kim
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

This work explores whether language models encode meaningfully grounded representations of sounds of objects. We learn a linear probe that retrieves the correct text representation of an object given a snippet of audio related to that object, where the sound representation is given by a pretrained audio model. This probe is trained via a contrastive loss that pushes the language representations and sound representations of an object to be close to one another. After training, the probe is tested on its ability to generalize to objects that were not seen during training. Across different language models and audio models, we find that the probe generalization is above chance in many cases, indicating that despite being trained only on raw text, language models encode grounded knowledge of sounds for some objects.

pdf bib
Leveraging Large Language Models for Learning Complex Legal Concepts through Storytelling
Hang Jiang | Xiajie Zhang | Robert Mahari | Daniel Kessler | Eric Ma | Tal August | Irene Li | Alex Pentland | Yoon Kim | Deb Roy | Jad Kabbara
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Making legal knowledge accessible to non-experts is crucial for enhancing general legal literacy and encouraging civic participation in democracy. However, legal documents are often challenging to understand for people without legal backgrounds. In this paper, we present a novel application of large language models (LLMs) in legal education to help non-experts learn intricate legal concepts through storytelling, an effective pedagogical tool in conveying complex and abstract concepts. We also introduce a new dataset LegalStories, which consists of 294 complex legal doctrines, each accompanied by a story and a set of multiple-choice questions generated by LLMs. To construct the dataset, we experiment with various LLMs to generate legal stories explaining these concepts. Furthermore, we use an expert-in-the-loop approach to iteratively design multiple-choice questions. Then, we evaluate the effectiveness of storytelling with LLMs through randomized controlled trials (RCTs) with legal novices on 10 samples from the dataset. We find that LLM-generated stories enhance comprehension of legal concepts and interest in law among non-native speakers compared to only definitions. Moreover, stories consistently help participants relate legal concepts to their lives. Finally, we find that learning with stories shows a higher retention rate for non-native speakers in the follow-up assessment. Our work has strong implications for using LLMs in promoting teaching and learning in the legal field and beyond.

pdf bib
Learning to Decode Collaboratively with Multiple Language Models
Zejiang Shen | Hunter Lang | Bailin Wang | Yoon Kim | David Sontag
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We propose a method to teach multiple large language models (LLM) to collaborate by interleaving their generations at the token level. We model the decision of which LLM generates the next token as a latent variable. By optimizing the marginal likelihood of a training set under our latent variable model, the base LLM automatically learns when to generate itself and when to call on one of the “assistant” language models to generate, all without direct supervision. Token-level collaboration during decoding allows for a fusion of each model’s expertise in a manner tailored to the specific task at hand. Our collaborative decoding is especially useful in cross-domain settings where a generalist base LLM learns to invoke domain expert models. On instruction-following, domain-specific QA, and reasoning tasks, we show that the performance of the joint system exceeds that of the individual models. Through qualitative analysis, we show models trained with our method exhibit several interesting collaboration patterns, e.g., template-filling, by visualizing the learned latent decisions.

2023

pdf bib
Unsupervised Discontinuous Constituency Parsing with Mildly Context-Sensitive Grammars
Songlin Yang | Roger Levy | Yoon Kim
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We study grammar induction with mildly context-sensitive grammars for unsupervised discontinuous parsing. Using the probabilistic linear context-free rewriting system (LCFRS) formalism, our approach fixes the rule structure in advance and focuses on parameter learning with maximum likelihood. To reduce the computational complexity of both parsing and parameter estimation, we restrict the grammar formalism to LCFRS-2 (i.e., binary LCFRS with fan-out two) and further discard rules that require O(l6) time to parse, reducing inference to O(l5). We find that using a large number of nonterminals is beneficial and thus make use of tensor decomposition-based rank-space dynamic programming with an embedding-based parameterization of rule probabilities to scale up the number of nonterminals. Experiments on German and Dutch show that our approach is able to induce linguistically meaningful trees with continuous and discontinuous structures.

pdf bib
Entailment as Robust Self-Learner
Jiaxin Ge | Hongyin Luo | Yoon Kim | James Glass
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Entailment has been recognized as an important metric for evaluating natural language understanding (NLU) models, and recent studies have found that entailment pretraining benefits weakly supervised fine-tuning. In this work, we design a prompting strategy that formulates a number of different NLU tasks as contextual entailment. This approach improves the zero-shot adaptation of pretrained entailment models. Secondly, we notice that self-training entailment-based models with unlabeled data can significantly improve the adaptation performance on downstream tasks. To achieve more stable improvement, we propose the Simple Pseudo-Label Editing (SimPLE) algorithm for better pseudo-labeling quality in self-training. We also found that both pretrained entailment-based models and the self-trained models are robust against adversarial evaluation data. Experiments on binary and multi-class classification tasks show that SimPLE leads to more robust self-training results, indicating that the self-trained entailment models are more efficient and trustworthy than large language models on language understanding tasks.

pdf bib
Deriving Language Models from Masked Language Models
Lucas Torroba Hennigen | Yoon Kim
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Masked language models (MLM) do not explicitly define a distribution over language, i.e., they are not language models per se. However, recent work has implicitly treated them as such for the purposes of generation and scoring. This paper studies methods for deriving explicit joint distributions from MLMs, focusing on distributions over two tokens, which makes it possible to calculate exact distributional properties. We find that an approach based on identifying joints whose conditionals are closest to those of the MLM works well and outperforms existing Markov random field-based approaches. We further find that this derived model’s conditionals can even occasionally outperform the original MLM’s conditionals.

pdf bib
Alignment via Mutual Information
Shinjini Ghosh | Yoon Kim | Ramon Fernandez Astudillo | Tahira Naseem | Jacob Andreas
Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)

Many language learning tasks require learners to infer correspondences between data in two modalities. Often, these alignments are many-to-many and context-sensitive. For example, translating into morphologically rich languages requires learning not just how words, but morphemes, should be translated; words and morphemes may have different meanings (or groundings) depending on the context in which they are used. We describe an information-theoretic approach to context-sensitive, many-to-many alignment. Our approach first trains a masked sequence model to place distributions over missing spans in (source, target) sequences. Next, it uses this model to compute pointwise mutual information between source and target spans conditional on context. Finally, it aligns spans with high mutual information. We apply this approach to two learning problems: character-based word translation (using alignments for joint morphological segmentation and lexicon learning) and visually grounded reference resolution (using alignments to jointly localize referents and learn word meanings). In both cases, our proposed approach outperforms both structured and neural baselines, showing that conditional mutual information offers an effective framework for formalizing alignment problems in general domains.

pdf bib
Simple Hardware-Efficient PCFGs with Independent Left and Right Productions
Wei Liu | Songlin Yang | Yoon Kim | Kewei Tu
Findings of the Association for Computational Linguistics: EMNLP 2023

Scaling dense PCFGs to thousands of nonterminals via low-rank parameterizations of the rule probability tensor has been shown to be beneficial for unsupervised parsing. However, PCFGs scaled this way still perform poorly as a language model, and even underperform similarly-sized HMMs. This work introduces SimplePCFG, a simple PCFG formalism with independent left and right productions. Despite imposing a stronger independence assumption than the low-rank approach, we find that this formalism scales more effectively both as a language model and as an unsupervised parser. We further introduce FlashInside, a hardware IO-aware implementation of the inside algorithm for efficiently scaling simple PCFGs. Through extensive experiments on multiple grammar induction benchmarks, we validate the effectiveness of simple PCFGs over low-rank baselines.

pdf bib
Explain-then-translate: an analysis on improving program translation with self-generated explanations
Zilu Tang | Mayank Agarwal | Alexander Shypula | Bailin Wang | Derry Wijaya | Jie Chen | Yoon Kim
Findings of the Association for Computational Linguistics: EMNLP 2023

This work explores the use of self-generated natural language explanations as an intermediate step for code-to-code translation with language models. Across three types of explanations and 19 programming languages constructed from the MultiPL-E dataset, we find the explanations to be particularly effective in the zero-shot case, improving performance by 12% on average. Improvements with natural language explanations are particularly pronounced on difficult programs. We release our dataset, code, and canonical solutions in all 19 languages.

pdf bib
Search Augmented Instruction Learning
Hongyin Luo | Tianhua Zhang | Yung-Sung Chuang | Yuan Gong | Yoon Kim | Xixin Wu | Helen Meng | James Glass
Findings of the Association for Computational Linguistics: EMNLP 2023

Large language models (LLMs) have been significantly improved by instruction fine-tuning, but still lack transparency and the ability to utilize up-to-date knowledge and information. In this work, we propose search-augmented instruction learning (SAIL), which grounds the language generation and instruction following abilities on complex search results generated by in-house and external search engines. With an instruction tuning corpus, we collect search results for each training case from different search APIs and domains, and construct a new search-grounded training set containing (instruction, grounding information, response) triplets. We then fine-tune the LLaMA-7B model on the constructed training set. Since the collected results contain unrelated and disputing languages, the model needs to learn to ground on trustworthy search results, filter out distracting passages, and generate the target response. The search result-denoising process entails explicit trustworthy information selection and multi-hop reasoning, since the retrieved passages might be informative but not contain the instruction-following answer. Experiments show that the fine-tuned SAIL-7B model has a strong instruction-following ability, and it performs significantly better on transparency-sensitive tasks, including open-ended question answering and fact checking.

2022

pdf bib
Inducing and Using Alignments for Transition-based AMR Parsing
Andrew Drozdov | Jiawei Zhou | Radu Florian | Andrew McCallum | Tahira Naseem | Yoon Kim | Ramón Astudillo
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Transition-based parsers for Abstract Meaning Representation (AMR) rely on node-to-word alignments. These alignments are learned separately from parser training and require a complex pipeline of rule-based components, pre-processing, and post-processing to satisfy domain-specific constraints. Parsers also train on a point-estimate of the alignment pipeline, neglecting the uncertainty due to the inherent ambiguity of alignment. In this work we explore two avenues for overcoming these limitations. First, we propose a neural aligner for AMR that learns node-to-word alignments without relying on complex pipelines. We subsequently explore a tighter integration of aligner and parser training by considering a distribution over oracle action sequences arising from aligner uncertainty. Empirical results show this approach leads to more accurate alignments and generalization better from the AMR2.0 to AMR3.0 corpora. We attain a new state-of-the art for gold-only trained models, matching silver-trained performance without the need for beam search on AMR3.0.

pdf bib
DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings
Yung-Sung Chuang | Rumen Dangovski | Hongyin Luo | Yang Zhang | Shiyu Chang | Marin Soljacic | Shang-Wen Li | Scott Yih | Yoon Kim | James Glass
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

We propose DiffCSE, an unsupervised contrastive learning framework for learning sentence embeddings. DiffCSE learns sentence embeddings that are sensitive to the difference between the original sentence and an edited sentence, where the edited sentence is obtained by stochastically masking out the original sentence and then sampling from a masked language model. We show that DiffSCE is an instance of equivariant contrastive learning, which generalizes contrastive learning and learns representations that are insensitive to certain types of augmentations and sensitive to other “harmful” types of augmentations. Our experiments show that DiffCSE achieves state-of-the-art results among unsupervised sentence representation learning methods, outperforming unsupervised SimCSE by 2.3 absolute points on semantic textual similarity tasks.

pdf bib
Large language models are few-shot clinical information extractors
Monica Agrawal | Stefan Hegselmann | Hunter Lang | Yoon Kim | David Sontag
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

A long-running goal of the clinical NLP community is the extraction of important variables trapped in clinical notes. However, roadblocks have included dataset shift from the general domain and a lack of public clinical corpora and annotations. In this work, we show that large language models, such as InstructGPT (Ouyang et al., 2022), perform well at zero- and few-shot information extraction from clinical text despite not being trained specifically for the clinical domain. Whereas text classification and generation performance have already been studied extensively in such models, here we additionally demonstrate how to leverage them to tackle a diverse set of NLP tasks which require more structured outputs, including span identification, token-level sequence classification, and relation extraction. Further, due to the dearth of available data to evaluate these systems, we introduce new datasets for benchmarking few-shot clinical information extraction based on a manual re-annotation of the CASI dataset (Moon et al., 2014) for new tasks. On the clinical extraction tasks we studied, the GPT-3 systems significantly outperform existing zero- and few-shot baselines.

pdf bib
Hierarchical Phrase-Based Sequence-to-Sequence Learning
Bailin Wang | Ivan Titov | Jacob Andreas | Yoon Kim
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

This paper describes a neural transducer that maintains the flexibility of standard sequence-to-sequence (seq2seq) models while incorporating hierarchical phrases as a source of inductive bias during training and as explicit constraints during inference. Our approach trains two models: a discriminative parser based on a bracketing transduction grammar whose derivation tree hierarchically aligns source and target phrases, and a neural seq2seq model that learns to translate the aligned phrases one-by-one. We use the same seq2seq model to translate at all phrase scales, which results in two inference modes: one mode in which the parser is discarded and only the seq2seq component is used at the sequence-level, and another in which the parser is combined with the seq2seq model. Decoding in the latter mode is done with the cube-pruned CKY algorithm, which is more involved but can make use of new translation rules during inference. We formalize our model as a source-conditioned synchronous grammar and develop an efficient variational inference algorithm for training. When applied on top of both randomly initialized and pretrained seq2seq models, we find that it performs well compared to baselines on small scale machine translation benchmarks.

pdf bib
Controlling the Focus of Pretrained Language Generation Models
Jiabao Ji | Yoon Kim | James Glass | Tianxing He
Findings of the Association for Computational Linguistics: ACL 2022

The finetuning of pretrained transformer-based language generation models are typically conducted in an end-to-end manner, where the model learns to attend to relevant parts of the input by itself. However, there does not exist a mechanism to directly control the model’s focus. This work aims to develop a control mechanism by which a user can select spans of context as “highlights” for the model to focus on, and generate relevant output. To achieve this goal, we augment a pretrained model with trainable “focus vectors” that are directly applied to the model’s embeddings, while the model itself is kept fixed. These vectors, trained on automatic annotations derived from attribution methods, act as indicators for context importance. We test our approach on two core generation tasks: dialogue response generation and abstractive summarization. We also collect evaluation data where the highlight-generation pairs are annotated by humans. Our experiments show that the trained focus vectors are effective in steering the model to generate outputs that are relevant to user-selected highlights.

pdf bib
Probing for Incremental Parse States in Autoregressive Language Models
Tiwalayo Eisape | Vineet Gangireddy | Roger Levy | Yoon Kim
Findings of the Association for Computational Linguistics: EMNLP 2022

Next-word predictions from autoregressive neural language models show remarkable sensitivity to syntax. This work evaluates the extent to which this behavior arises as a result of a learned ability to maintain implicit representations of incremental syntactic structures. We extend work in syntactic probing to the incremental setting and present several probes for extracting incomplete syntactic structure (operationalized through parse states from a stack-based parser) from autoregressive language models. We find that our probes can be used to predict model preferences on ambiguous sentence prefixes and causally intervene on model representations and steer model behavior. This suggests implicit incremental syntactic inferences underlie next-word predictions in autoregressive neural language models.

pdf bib
Proceedings of the Workshop on Unimodal and Multimodal Induction of Linguistic Structures (UM-IoS)
Wenjuan Han | Zilong Zheng | Zhouhan Lin | Lifeng Jin | Yikang Shen | Yoon Kim | Kewei Tu
Proceedings of the Workshop on Unimodal and Multimodal Induction of Linguistic Structures (UM-IoS)

2021

pdf bib
Parameter-Efficient Transfer Learning with Diff Pruning
Demi Guo | Alexander Rush | Yoon Kim
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

The large size of pretrained networks makes them difficult to deploy for multiple tasks in storage-constrained settings. Diff pruning enables parameter-efficient transfer learning that scales well with new tasks. The approach learns a task-specific “diff” vector that extends the original pretrained parameters. This diff vector is adaptively pruned during training with a differentiable approximation to the L0-norm penalty to encourage sparsity. As the number of tasks increases, diff pruning remains parameter-efficient, as it requires storing only a small diff vector for each task. Since it does not require access to all tasks during training, it is attractive in on-device deployment settings where tasks arrive in stream or even from different providers. Diff pruning can match the performance of finetuned baselines on the GLUE benchmark while only modifying 0.5% of the pretrained model’s parameters per task and scales favorably in comparison to popular pruning approaches.

pdf bib
Syntactic Perturbations Reveal Representational Correlates of Hierarchical Phrase Structure in Pretrained Language Models
Matteo Alleman | Jonathan Mamou | Miguel A Del Rio | Hanlin Tang | Yoon Kim | SueYeon Chung
Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)

While vector-based language representations from pretrained language models have set a new standard for many NLP tasks, there is not yet a complete accounting of their inner workings. In particular, it is not entirely clear what aspects of sentence-level syntax are captured by these representations, nor how (if at all) they are built along the stacked layers of the network. In this paper, we aim to address such questions with a general class of interventional, input perturbation-based analyses of representations from pretrained language models. Importing from computational and cognitive neuroscience the notion of representational invariance, we perform a series of probes designed to test the sensitivity of these representations to several kinds of structure in sentences. Each probe involves swapping words in a sentence and comparing the representations from perturbed sentences against the original. We experiment with three different perturbations: (1) random permutations of n-grams of varying width, to test the scale at which a representation is sensitive to word position; (2) swapping of two spans which do or do not form a syntactic phrase, to test sensitivity to global phrase structure; and (3) swapping of two adjacent words which do or do not break apart a syntactic phrase, to test sensitivity to local phrase structure. Results from these probes collectively suggest that Transformers build sensitivity to larger parts of the sentence along their layers, and that hierarchical phrase structure plays a role in this process. More broadly, our results also indicate that structured input perturbations widens the scope of analyses that can be performed on often-opaque deep learning systems, and can serve as a complement to existing tools (such as supervised linear probes) for interpreting complex black-box models.

2020

pdf bib
Sequence-Level Mixed Sample Data Augmentation
Demi Guo | Yoon Kim | Alexander Rush
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Despite their empirical success, neural networks still have difficulty capturing compositional aspects of natural language. This work proposes a simple data augmentation approach to encourage compositional behavior in neural models for sequence-to-sequence problems. Our approach, SeqMix, creates new synthetic examples by softly combining input/output sequences from the training set. We connect this approach to existing techniques such as SwitchOut and word dropout, and show that these techniques are all essentially approximating variants of a single objective. SeqMix consistently yields approximately 1.0 BLEU improvement on five different translation datasets over strong Transformer baselines. On tasks that require strong compositional generalization such as SCAN and semantic parsing, SeqMix also offers further improvements.

2019

pdf bib
Compound Probabilistic Context-Free Grammars for Grammar Induction
Yoon Kim | Chris Dyer | Alexander Rush
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

We study a formalization of the grammar induction problem that models sentences as being generated by a compound probabilistic context free grammar. In contrast to traditional formulations which learn a single stochastic grammar, our context-free rule probabilities are modulated by a per-sentence continuous latent variable, which induces marginal dependencies beyond the traditional context-free assumptions. Inference in this context-dependent grammar is performed by collapsed variational inference, in which an amortized variational posterior is placed on the continuous variable, and the latent trees are marginalized with dynamic programming. Experiments on English and Chinese show the effectiveness of our approach compared to recent state-of-the-art methods for grammar induction from words with neural language models.

pdf bib
Unsupervised Recurrent Neural Network Grammars
Yoon Kim | Alexander Rush | Lei Yu | Adhiguna Kuncoro | Chris Dyer | Gábor Melis
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Recurrent neural network grammars (RNNG) are generative models of language which jointly model syntax and surface structure by incrementally generating a syntax tree and sentence in a top-down, left-to-right order. Supervised RNNGs achieve strong language modeling and parsing performance, but require an annotated corpus of parse trees. In this work, we experiment with unsupervised learning of RNNGs. Since directly marginalizing over the space of latent trees is intractable, we instead apply amortized variational inference. To maximize the evidence lower bound, we develop an inference network parameterized as a neural CRF constituency parser. On language modeling, unsupervised RNNGs perform as well their supervised counterparts on benchmarks in English and Chinese. On constituency grammar induction, they are competitive with recent neural language models that induce tree structures from words through attention mechanisms.

2018

pdf bib
OpenNMT: Neural Machine Translation Toolkit
Guillaume Klein | Yoon Kim | Yuntian Deng | Vincent Nguyen | Jean Senellart | Alexander Rush
Proceedings of the 13th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)

bib
Deep Latent Variable Models of Natural Language
Alexander Rush | Yoon Kim | Sam Wiseman
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts

The proposed tutorial will cover deep latent variable models both in the case where exact inference over the latent variables is tractable and when it is not. The former case includes neural extensions of unsupervised tagging and parsing models. Our discussion of the latter case, where inference cannot be performed tractably, will restrict itself to continuous latent variables. In particular, we will discuss recent developments both in neural variational inference (e.g., relating to Variational Auto-encoders) and in implicit density modeling (e.g., relating to Generative Adversarial Networks). We will highlight the challenges of applying these families of methods to NLP problems, and discuss recent successes and best practices.

2017

pdf bib
Adapting Sequence Models for Sentence Correction
Allen Schmaltz | Yoon Kim | Alexander Rush | Stuart Shieber
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

In a controlled experiment of sequence-to-sequence approaches for the task of sentence correction, we find that character-based models are generally more effective than word-based models and models that encode subword information via convolutions, and that modeling the output data as a series of diffs improves effectiveness over standard approaches. Our strongest sequence-to-sequence model improves over our strongest phrase-based statistical machine translation model, with access to the same data, by 6 M2 (0.5 GLEU) points. Additionally, in the data environment of the standard CoNLL-2014 setup, we demonstrate that modeling (and tuning against) diffs yields similar or better M2 scores with simpler models and/or significantly less data than previous sequence-to-sequence approaches.

pdf bib
OpenNMT: Open-Source Toolkit for Neural Machine Translation
Guillaume Klein | Yoon Kim | Yuntian Deng | Jean Senellart | Alexander Rush
Proceedings of ACL 2017, System Demonstrations

2016

pdf bib
Sequence-Level Knowledge Distillation
Yoon Kim | Alexander M. Rush
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

pdf bib
Sentence-Level Grammatical Error Identification as Sequence-to-Sequence Correction
Allen Schmaltz | Yoon Kim | Alexander M. Rush | Stuart Shieber
Proceedings of the 11th Workshop on Innovative Use of NLP for Building Educational Applications

2014

pdf bib
Temporal Analysis of Language through Neural Language Models
Yoon Kim | Yi-I Chiu | Kentaro Hanaki | Darshan Hegde | Slav Petrov
Proceedings of the ACL 2014 Workshop on Language Technologies and Computational Social Science

pdf bib
Credibility Adjusted Term Frequency: A Supervised Term Weighting Scheme for Sentiment Analysis and Text Classification
Yoon Kim | Owen Zhang
Proceedings of the 5th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis

pdf bib
Convolutional Neural Networks for Sentence Classification
Yoon Kim
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Search