Hiroshi Noji


2023

pdf bib
How Much Syntactic Supervision is “Good Enough”?
Hiroshi Noji | Yohei Oseki
Findings of the Association for Computational Linguistics: EACL 2023

In this paper, we explore how much syntactic supervision is “good enough” to make language models (LMs) more human-like. Specifically, we propose the new method called syntactic ablation, where syntactic LMs, namely Recurrent Neural Network Grammars (RNNGs), are gradually ablated from full syntactic supervision to zero syntactic supervision (≈ unidirectional LSTM) by preserving NP, VP, PP, SBAR nonterminal symbols and the combinations thereof. The 17 ablated grammars are then evaluated via targeted syntactic evaluation on the SyntaxGym benchmark. The results of our syntactic ablation demonstrated that (i) the RNNG with zero syntactic supervision underperformed the RNNGs with some syntactic supervision, (ii) the RNNG with full syntactic supervision underperformed the RNNGs with less syntactic supervision, and (iii) the RNNG with mild syntactic supervision achieved the best performance comparable to the state-of-the-art GPT-2-XL. Those results may suggest that the “good enough” approach to language processing seems to make LMs more human-like.

2022

pdf bib
Multilingual Syntax-aware Language Modeling through Dependency Tree Conversion
Shunsuke Kando | Hiroshi Noji | Yusuke Miyao
Proceedings of the Sixth Workshop on Structured Prediction for NLP

Incorporating stronger syntactic biases into neural language models (LMs) is a long-standing goal, but research in this area often focuses on modeling English text, where constituent treebanks are readily available. Extending constituent tree-based LMs to the multilingual setting, where dependency treebanks are more common, is possible via dependency-to-constituency conversion methods. However, this raises the question of which tree formats are best for learning the model, and for which languages. We investigate this question by training recurrent neural network grammars (RNNGs) using various conversion methods, and evaluating them empirically in a multilingual setting. We examine the effect on LM performance across nine conversion methods and five languages through seven types of syntactic tests. On average, the performance of our best model represents a 19 % increase in accuracy over the worst choice across all languages. Our best model shows the advantage over sequential/overparameterized LMs, suggesting the positive effect of syntax injection in a multilingual setting. Our experiments highlight the importance of choosing the right tree formalism, and provide insights into making an informed decision.

2021

pdf bib
Generating Racing Game Commentary from Vision, Language, and Structured Data
Tatsuya Ishigaki | Goran Topic | Yumi Hamazono | Hiroshi Noji | Ichiro Kobayashi | Yusuke Miyao | Hiroya Takamura
Proceedings of the 14th International Conference on Natural Language Generation

We propose the task of automatically generating commentaries for races in a motor racing game, from vision, structured numerical, and textual data. Commentaries provide information to support spectators in understanding events in races. Commentary generation models need to interpret the race situation and generate the correct content at the right moment. We divide the task into two subtasks: utterance timing identification and utterance generation. Because existing datasets do not have such alignments of data in multiple modalities, this setting has not been explored in depth. In this study, we introduce a new large-scale dataset that contains aligned video data, structured numerical data, and transcribed commentaries that consist of 129,226 utterances in 1,389 races in a game. Our analysis reveals that the characteristics of commentaries change over time or from viewpoints. Our experiments on the subtasks show that it is still challenging for a state-of-the-art vision encoder to capture useful information from videos to generate accurate commentaries. We make the dataset and baseline implementation publicly available for further research.

pdf bib
Modeling Human Sentence Processing with Left-Corner Recurrent Neural Network Grammars
Ryo Yoshida | Hiroshi Noji | Yohei Oseki
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

In computational linguistics, it has been shown that hierarchical structures make language models (LMs) more human-like. However, the previous literature has been agnostic about a parsing strategy of the hierarchical models. In this paper, we investigated whether hierarchical structures make LMs more human-like, and if so, which parsing strategy is most cognitively plausible. In order to address this question, we evaluated three LMs against human reading times in Japanese with head-final left-branching structures: Long Short-Term Memory (LSTM) as a sequential model and Recurrent Neural Network Grammars (RNNGs) with top-down and left-corner parsing strategies as hierarchical models. Our computational modeling demonstrated that left-corner RNNGs outperformed top-down RNNGs and LSTM, suggesting that hierarchical and left-corner architectures are more cognitively plausible than top-down or sequential architectures. In addition, the relationships between the cognitive plausibility and (i) perplexity, (ii) parsing, and (iii) beam size will also be discussed.

pdf bib
Effective Batching for Recurrent Neural Network Grammars
Hiroshi Noji | Yohei Oseki
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

2020

pdf bib
Market Comment Generation from Data with Noisy Alignments
Yumi Hamazono | Yui Uehara | Hiroshi Noji | Yusuke Miyao | Hiroya Takamura | Ichiro Kobayashi
Proceedings of the 13th International Conference on Natural Language Generation

End-to-end models on data-to-text learn the mapping of data and text from the aligned pairs in the dataset. However, these alignments are not always obtained reliably, especially for the time-series data, for which real time comments are given to some situation and there might be a delay in the comment delivery time compared to the actual event time. To handle this issue of possible noisy alignments in the dataset, we propose a neural network model with multi-timestep data and a copy mechanism, which allows the models to learn the correspondences between data and text from the dataset with noisier alignments. We focus on generating market comments in Japanese that are delivered each time an event occurs in the market. The core idea of our approach is to utilize multi-timestep data, which is not only the latest market price data when the comment is delivered, but also the data obtained at several timesteps earlier. On top of this, we employ a copy mechanism that is suitable for referring to the content of data records in the market price data. We confirm the superiority of our proposal by two evaluation metrics and show the accuracy improvement of the sentence generation using the time series data by our proposed method.

pdf bib
Learning with Contrastive Examples for Data-to-Text Generation
Yui Uehara | Tatsuya Ishigaki | Kasumi Aoki | Hiroshi Noji | Keiichi Goshima | Ichiro Kobayashi | Hiroya Takamura | Yusuke Miyao
Proceedings of the 28th International Conference on Computational Linguistics

Existing models for data-to-text tasks generate fluent but sometimes incorrect sentences e.g., “Nikkei gains” is generated when “Nikkei drops” is expected. We investigate models trained on contrastive examples i.e., incorrect sentences or terms, in addition to correct ones to reduce such errors. We first create rules to produce contrastive examples from correct ones by replacing frequent crucial terms such as “gain” or “drop”. We then use learning methods with several losses that exploit contrastive examples. Experiments on the market comment generation task show that 1) exploiting contrastive examples improves the capability of generating sentences with better lexical choice, without degrading the fluency, 2) the choice of the loss function is an important factor because the performances on different metrics depend on the types of loss functions, and 3) the use of the examples produced by some specific rules further improves performance. Human evaluation also supports the effectiveness of using contrastive examples.

pdf bib
An empirical analysis of existing systems and datasets toward general simple question answering
Namgi Han | Goran Topic | Hiroshi Noji | Hiroya Takamura | Yusuke Miyao
Proceedings of the 28th International Conference on Computational Linguistics

In this paper, we evaluate the progress of our field toward solving simple factoid questions over a knowledge base, a practically important problem in natural language interface to database. As in other natural language understanding tasks, a common practice for this task is to train and evaluate a model on a single dataset, and recent studies suggest that SimpleQuestions, the most popular and largest dataset, is nearly solved under this setting. However, this common setting does not evaluate the robustness of the systems outside of the distribution of the used training data. We rigorously evaluate such robustness of existing systems using different datasets. Our analysis, including shifting of training and test datasets and training on a union of the datasets, suggests that our progress in solving SimpleQuestions dataset does not indicate the success of more general simple question answering. We discuss a possible future direction toward this goal.

pdf bib
CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters
Hicham El Boukkouri | Olivier Ferret | Thomas Lavergne | Hiroshi Noji | Pierre Zweigenbaum | Jun’ichi Tsujii
Proceedings of the 28th International Conference on Computational Linguistics

Due to the compelling improvements brought by BERT, many recent representation models adopted the Transformer architecture as their main building block, consequently inheriting the wordpiece tokenization system despite it not being intrinsically linked to the notion of Transformers. While this system is thought to achieve a good balance between the flexibility of characters and the efficiency of full words, using predefined wordpiece vocabularies from the general domain is not always suitable, especially when building models for specialized domains (e.g., the medical domain). Moreover, adopting a wordpiece tokenization shifts the focus from the word level to the subword level, making the models conceptually more complex and arguably less convenient in practice. For these reasons, we propose CharacterBERT, a new variant of BERT that drops the wordpiece system altogether and uses a Character-CNN module instead to represent entire words by consulting their characters. We show that this new model improves the performance of BERT on a variety of medical domain tasks while at the same time producing robust, word-level, and open-vocabulary representations.

pdf bib
An Analysis of the Utility of Explicit Negative Examples to Improve the Syntactic Abilities of Neural Language Models
Hiroshi Noji | Hiroya Takamura
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

We explore the utilities of explicit negative examples in training neural language models. Negative examples here are incorrect words in a sentence, such as barks in *The dogs barks. Neural language models are commonly trained only on positive examples, a set of sentences in the training data, but recent studies suggest that the models trained in this way are not capable of robustly handling complex syntactic constructions, such as long-distance agreement. In this paper, we first demonstrate that appropriately using negative examples about particular constructions (e.g., subject-verb agreement) will boost the model’s robustness on them in English, with a negligible loss of perplexity. The key to our success is an additional margin loss between the log-likelihoods of a correct word and an incorrect word. We then provide a detailed analysis of the trained models. One of our findings is the difficulty of object-relative clauses for RNNs. We find that even with our direct learning signals the models still suffer from resolving agreement across an object-relative clause. Augmentation of training sentences involving the constructions somewhat helps, but the accuracy still does not reach the level of subject-relative clauses. Although not directly cognitively appealing, our method can be a tool to analyze the true architectural limitation of neural models on challenging linguistic constructions.

2019

pdf bib
Automatic Generation of High Quality CCGbanks for Parser Domain Adaptation
Masashi Yoshikawa | Hiroshi Noji | Koji Mineshima | Daisuke Bekki
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

We propose a new domain adaptation method for Combinatory Categorial Grammar (CCG) parsing, based on the idea of automatic generation of CCG corpora exploiting cheaper resources of dependency trees. Our solution is conceptually simple, and not relying on a specific parser architecture, making it applicable to the current best-performing parsers. We conduct extensive parsing experiments with detailed discussion; on top of existing benchmark datasets on (1) biomedical texts and (2) question sentences, we create experimental datasets of (3) speech conversation and (4) math problems. When applied to the proposed method, an off-the-shelf CCG parser shows significant performance gains, improving from 90.7% to 96.6% on speech conversation, and from 88.5% to 96.8% on math problems.

pdf bib
Learning to Select, Track, and Generate for Data-to-Text
Hayate Iso | Yui Uehara | Tatsuya Ishigaki | Hiroshi Noji | Eiji Aramaki | Ichiro Kobayashi | Yusuke Miyao | Naoaki Okazaki | Hiroya Takamura
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

We propose a data-to-text generation model with two modules, one for tracking and the other for text generation. Our tracking module selects and keeps track of salient information and memorizes which record has been mentioned. Our generation module generates a summary conditioned on the state of tracking module. Our proposed model is considered to simulate the human-like writing process that gradually selects the information by determining the intermediate variables while writing the summary. In addition, we also explore the effectiveness of the writer information for generations. Experimental results show that our proposed model outperforms existing models in all evaluation metrics even without writer information. Incorporating writer information further improves the performance, contributing to content planning and surface realization.

pdf bib
Controlling Contents in Data-to-Document Generation with Human-Designed Topic Labels
Kasumi Aoki | Akira Miyazawa | Tatsuya Ishigaki | Tatsuya Aoki | Hiroshi Noji | Keiichi Goshima | Ichiro Kobayashi | Hiroya Takamura | Yusuke Miyao
Proceedings of the 12th International Conference on Natural Language Generation

We propose a data-to-document generator that can easily control the contents of output texts based on a neural language model. Conventional data-to-text model is useful when a reader seeks a global summary of data because it has only to describe an important part that has been extracted beforehand. However, because depending on users, it differs what they are interested in, so it is necessary to develop a method to generate various summaries according to users’ interests. We develop a model to generate various summaries and to control their contents by providing the explicit targets for a reference to the model as controllable factors. In the experiments, we used five-minute or one-hour charts of 9 indicators (e.g., Nikkei225), as time-series data, and daily summaries of Nikkei Quick News as textual data. We conducted comparative experiments using two pieces of information: human-designed topic labels indicating the contents of a sentence and automatically extracted keywords as the referential information for generation.

2018

pdf bib
Dynamic Feature Selection with Attention in Incremental Parsing
Ryosuke Kohita | Hiroshi Noji | Yuji Matsumoto
Proceedings of the 27th International Conference on Computational Linguistics

One main challenge for incremental transition-based parsers, when future inputs are invisible, is to extract good features from a limited local context. In this work, we present a simple technique to maximally utilize the local features with an attention mechanism, which works as context- dependent dynamic feature selection. Our model learns, for example, which tokens should a parser focus on, to decide the next action. Our multilingual experiment shows its effectiveness across many languages. We also present an experiment with augmented test dataset and demon- strate it helps to understand the model’s behavior on locally ambiguous points.

pdf bib
An Empirical Investigation of Error Types in Vietnamese Parsing
Quy Nguyen | Yusuke Miyao | Hiroshi Noji | Nhung Nguyen
Proceedings of the 27th International Conference on Computational Linguistics

Syntactic parsing plays a crucial role in improving the quality of natural language processing tasks. Although there have been several research projects on syntactic parsing in Vietnamese, the parsing quality has been far inferior than those reported in major languages, such as English and Chinese. In this work, we evaluated representative constituency parsing models on a Vietnamese Treebank to look for the most suitable parsing method for Vietnamese. We then combined the advantages of automatic and manual analysis to investigate errors produced by the experimented parsers and find the reasons for them. Our analysis focused on three possible sources of parsing errors, namely limited training data, part-of-speech (POS) tagging errors, and ambiguous constructions. As a result, we found that the last two sources, which frequently appear in Vietnamese text, significantly attributed to the poor performance of Vietnamese parsing.

pdf bib
Consistent CCG Parsing over Multiple Sentences for Improved Logical Reasoning
Masashi Yoshikawa | Koji Mineshima | Hiroshi Noji | Daisuke Bekki
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)

In formal logic-based approaches to Recognizing Textual Entailment (RTE), a Combinatory Categorial Grammar (CCG) parser is used to parse input premises and hypotheses to obtain their logical formulas. Here, it is important that the parser processes the sentences consistently; failing to recognize the similar syntactic structure results in inconsistent predicate argument structures among them, in which case the succeeding theorem proving is doomed to failure. In this work, we present a simple method to extend an existing CCG parser to parse a set of sentences consistently, which is achieved with an inter-sentence modeling with Markov Random Fields (MRF). When combined with existing logic-based systems, our method always shows improvement in the RTE experiments on English and Japanese languages.

2017

pdf bib
Effective Online Reordering with Arc-Eager Transitions
Ryosuke Kohita | Hiroshi Noji | Yuji Matsumoto
Proceedings of the 15th International Conference on Parsing Technologies

We present a new transition system with word reordering for unrestricted non-projective dependency parsing. Our system is based on decomposed arc-eager rather than arc-standard, which allows more flexible ambiguity resolution between a local projective and non-local crossing attachment. In our experiment on Universal Dependencies 2.0, we find our parser outperforms the ordinary swap-based parser particularly on languages with a large amount of non-projectivity.

pdf bib
Multilingual Back-and-Forth Conversion between Content and Function Head for Easy Dependency Parsing
Ryosuke Kohita | Hiroshi Noji | Yuji Matsumoto
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers

Universal Dependencies (UD) is becoming a standard annotation scheme cross-linguistically, but it is argued that this scheme centering on content words is harder to parse than the conventional one centering on function words. To improve the parsability of UD, we propose a back-and-forth conversion algorithm, in which we preprocess the training treebank to increase parsability, and reconvert the parser outputs to follow the UD scheme as a postprocess. We show that this technique consistently improves LAS across languages even with a state-of-the-art parser, in particular on core dependency arcs such as nominal modifier. We also provide an in-depth analysis to understand why our method increases parsability.

pdf bib
A* CCG Parsing with a Supertag and Dependency Factored Model
Masashi Yoshikawa | Hiroshi Noji | Yuji Matsumoto
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We propose a new A* CCG parsing model in which the probability of a tree is decomposed into factors of CCG categories and its syntactic dependencies both defined on bi-directional LSTMs. Our factored model allows the precomputation of all probabilities and runs very efficiently, while modeling sentence structures explicitly via dependencies. Our model achieves the state-of-the-art results on English and Japanese CCG parsing.

pdf bib
Adversarial Training for Cross-Domain Universal Dependency Parsing
Motoki Sato | Hitoshi Manabe | Hiroshi Noji | Yuji Matsumoto
Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies

We describe our submission to the CoNLL 2017 shared task, which exploits the shared common knowledge of a language across different domains via a domain adaptation technique. Our approach is an extension to the recently proposed adversarial training technique for domain adaptation, which we apply on top of a graph-based neural dependency parsing model on bidirectional LSTMs. In our experiments, we find our baseline graph-based parser already outperforms the official baseline model (UDPipe) by a large margin. Further, by applying our technique to the treebanks of the same language with different domains, we observe an additional gain in the performance, in particular for the domains with less training data.

pdf bib
Can Discourse Relations be Identified Incrementally?
Frances Yung | Hiroshi Noji | Yuji Matsumoto
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

Humans process language word by word and construct partial linguistic structures on the fly before the end of the sentence is perceived. Inspired by this cognitive ability, incremental algorithms for natural language processing tasks have been proposed and demonstrated promising performance. For discourse relation (DR) parsing, however, it is not yet clear to what extent humans can recognize DRs incrementally, because the latent ‘nodes’ of discourse structure can span clauses and sentences. To answer this question, this work investigates incrementality in discourse processing based on a corpus annotated with DR signals. We find that DRs are dominantly signaled at the boundary between the two constituent discourse units. The findings complement existing psycholinguistic theories on expectation in discourse processing and provide direction for incremental discourse parsing.

2016

pdf bib
Jigg: A Framework for an Easy Natural Language Processing Pipeline
Hiroshi Noji | Yusuke Miyao
Proceedings of ACL-2016 System Demonstrations

pdf bib
Using Left-corner Parsing to Encode Universal Structural Constraints in Grammar Induction
Hiroshi Noji | Yusuke Miyao | Mark Johnson
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

2015

pdf bib
Optimal Shift-Reduce Constituent Parsing with Structured Perceptron
Le Quang Thang | Hiroshi Noji | Yusuke Miyao
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

2014

pdf bib
Left-corner Transitions on Dependency Parsing
Hiroshi Noji | Yusuke Miyao
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers

2013

pdf bib
Improvements to the Bayesian Topic N-Gram Models
Hiroshi Noji | Daichi Mochihashi | Yusuke Miyao
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing