In document-level neural machine translation (DocNMT), multi-encoder approaches are common in encoding context and source sentences. Recent studies (CITATION) have shown that the context encoder generates noise and makes the model robust to the choice of context. This paper further investigates this observation by explicitly modelling context encoding through multi-task learning (MTL) to make the model sensitive to the choice of context. We conduct experiments on cascade MTL architecture, which consists of one encoder and two decoders. Generation of the source from the context is considered an auxiliary task, and generation of the target from the source is the main task. We experimented with German–English language pairs on News, TED, and Europarl corpora. Evaluation results show that the proposed MTL approach performs better than concatenation-based and multi-encoder DocNMT models in low-resource settings and is sensitive to the choice of context. However, we observe that the MTL models are failing to generate the source from the context. These observations align with the previous studies, and this might suggest that the available document-level parallel corpora are not context-aware, and a robust sentence-level model can outperform the context-aware models.
In this paper, we present Team Hawk’s participation in Track 1 of the WASSA 2023 shared task. The objective of the task is to understand the empathy that emerges between individuals during their conversations. In our study, we developed a multi-tasking framework that is capable of automatically assessing empathy, intensity of emotion, and polarity of emotion within participants’ conversations. Our proposed core model extends the transformer architecture, utilizing two separate RoBERTa-based encoders to encode both the articles and conversations. Subsequently, a sequence of self-attention, position-wise feed-forward, and dense layers are employed to predict the regression scores for the three sub-tasks: empathy, intensity of emotion, and polarity of emotion. Our best model achieved average Pearson’s correlation of 0.7710 (Empathy: 0.7843, Emotion Polarity: 0.7917, Emotion Intensity: 0.7381) on the released development set and 0.7250 (Empathy: 0.8090, Emotion Polarity: 0.7010, Emotion Intensity: 0.6650) on the released test set. These results earned us the 3rd position in the test set evaluation phase of Track 1.
This paper presents the results of the low-resource Indic language translation task organized alongside the Eighth Conference on Machine Translation (WMT) 2023. In this task, participants were asked to build machine translation systems for any of four language pairs, namely, English-Assamese, English-Mizo, English-Khasi, and English-Manipuri. For this task, the IndicNE-Corp1.0 dataset is released, which consists of parallel and monolingual corpora for northeastern Indic languages such as Assamese, Mizo, Khasi, and Manipuri. The evaluation will be carried out using automatic evaluation metrics (BLEU, TER, RIBES, COMET, ChrF) and human evaluation.
Even though, machine translation has seen huge improvements in the the last decade, translation quality for Indic languages is still underwhelming, which is attributed to the small amount of parallel data available. In this paper, we present our approach to mitigate the issue of the low amount of parallel training data availability for Indic languages, especially for the language pair English-Manipuri and Assamese-English. Our primary submission for the Manipuri-to-English translation task provided the best scoring system for this language direction. We describe about the systems we built in detail and our findings in the process.
Recent studies have shown that the multi-encoder models are agnostic to the choice of context and the context encoder generates noise which helps in the improvement of the models in terms of BLEU score. In this paper, we further explore this idea by evaluating with context-aware pronoun translation test set by training multi-encoder models trained on three different context settings viz, previous two sentences, random two sentences, and a mix of both as context. Specifically, we evaluate the models on the ContraPro test set to study how different contexts affect pronoun translation accuracy. The results show that the model can perform well on the ContraPro test set even when the context is random. We also analyze the source representations to study whether the context encoder is generating noise or not. Our analysis shows that the context encoder is providing sufficient information to learn discourse-level information. Additionally, we observe that mixing the selected context (the previous two sentences in this case) and the random context is generally better than the other settings.
Multilingual country like India has an enormous linguistic diversity and has an increasing demand towards developing language resources such that it will outreach in various natural language processing applications like machine translation. Low-resource language translation possesses challenges in the field of machine translation. The challenges include the availability of corpus and differences in linguistic information. This paper investigates a low-resource language pair, English-to-Mizo exploring neural machine translation by contributing an Indian language resource, i.e., English-Mizo corpus. In this work, we explore one of the main challenges to tackling tonal words existing in the Mizo language, as they add to the complexity on top of low-resource challenges for any natural language processing task. Our approach improves translation accuracy by encountering tonal words of Mizo and achieved a state-of-the-art result in English-to-Mizo translation.
Image Captioning as a task that has seen major updates over time. In recent methods, visual-linguistic grounding of the image-text pair is leveraged. This includes either generating the textual description of the objects and entities present within the image in constrained manner, or generating detailed description of these entities as a paragraph. But there is still a long way to go towards being able to generate text that is not only semantically richer, but also contains real world knowledge in it. This is the motivation behind exploring image2tweet generation through the lens of existing image-captioning approaches. At the same time, there is little research in image captioning in Indian languages like Hindi. In this paper, we release Hindi and English datasets for the task of tweet generation given an image. The aim is to generate a specialized text like a tweet, that is not a direct result of visual-linguistic grounding that is usually leveraged in similar tasks, but conveys a message that factors-in not only the visual content of the image, but also additional real world contextual information associated with the event described within the image as closely as possible. Further, We provide baseline DL models on our data and invite researchers to build more sophisticated systems for the problem.
This paper presents the results of the newstranslation task, the multilingual low-resourcetranslation for Indo-European languages, thetriangular translation task, and the automaticpost-editing task organised as part of the Con-ference on Machine Translation (WMT) 2021.In the news task, participants were asked tobuild machine translation systems for any of10 language pairs, to be evaluated on test setsconsisting mainly of news stories. The taskwas also opened up to additional test suites toprobe specific aspects of translation.
In automatic post-editing (APE) it makes sense to condition post-editing (pe) decisions on both the source (src) and the machine translated text (mt) as input. This has led to multi-encoder based neural APE approaches. A research challenge now is the search for architectures that best support the capture, preparation and provision of src and mt information and its integration with pe decisions. In this paper we present an efficient multi-encoder based APE model, called transference. Unlike previous approaches, it (i) uses a transformer encoder block for src, (ii) followed by a decoder block, but without masking for self-attention on mt, which effectively acts as second encoder combining src –> mt, and (iii) feeds this representation into a final decoder block generating pe. Our model outperforms the best performing systems by 1 BLEU point on the WMT 2016, 2017, and 2018 English–German APE shared tasks (PBSMT and NMT). Furthermore, the results of our model on the WMT 2019 APE task using NMT data shows a comparable performance to the state-of-the-art system. The inference time of our model is similar to the vanilla transformer-based NMT system although our model deals with two separate encoders. We further investigate the importance of our newly introduced second encoder and find that a too small amount of layers does hurt the performance, while reducing the number of layers of the decoder does not matter much.
This paper presents the results of the news translation task and the similar language translation task, both organised alongside the Conference on Machine Translation (WMT) 2020. In the news task, participants were asked to build machine translation systems for any of 11 language pairs, to be evaluated on test sets consisting mainly of news stories. The task was also opened up to additional test suites to probe specific aspects of translation. In the similar language translation task, participants built machine translation systems for translating between closely related pairs of languages.
In this paper we present the WIPRO-RIT systems submitted to the Similar Language Translation shared task at WMT 2020. The second edition of this shared task featured parallel data from pairs/groups of similar languages from three different language families: Indo-Aryan languages (Hindi and Marathi), Romance languages (Catalan, Portuguese, and Spanish), and South Slavic Languages (Croatian, Serbian, and Slovene). We report the results obtained by our systems in translating from Hindi to Marathi and from Marathi to Hindi. WIPRO-RIT achieved competitive performance ranking 1st in Marathi to Hindi and 2nd in Hindi to Marathi translation among 22 systems.
Current advances in machine translation (MT) increase the need for translators to switch from traditional translation to post-editing (PE) of machine-translated text, a process that saves time and reduces errors. This affects the design of translation interfaces, as the task changes from mainly generating text to correcting errors within otherwise helpful translation proposals. Since this paradigm shift offers potential for modalities other than mouse and keyboard, we present MMPE, the first prototype to combine traditional input modes with pen, touch, and speech modalities for PE of MT. The results of an evaluation with professional translators suggest that pen and touch interaction are suitable for deletion and reordering tasks, while they are of limited use for longer insertions. On the other hand, speech and multi-modal combinations of select & speech are considered suitable for replacements and insertions but offer less potential for deletion and reordering. Overall, participants were enthusiastic about the new modalities and saw them as good extensions to mouse & keyboard, but not as a complete substitute.
The shift from traditional translation to post-editing (PE) of machine-translated (MT) text can save time and reduce errors, but it also affects the design of translation interfaces, as the task changes from mainly generating text to correcting errors within otherwise helpful translation proposals. Since this paradigm shift offers potential for modalities other than mouse and keyboard, we present MMPE, the first prototype to combine traditional input modes with pen, touch, and speech modalities for PE of MT. Users can directly cross out or hand-write new text, drag and drop words for reordering, or use spoken commands to update the text in place. All text manipulations are logged in an easily interpretable format to simplify subsequent translation process research. The results of an evaluation with professional translators suggest that pen and touch interaction are suitable for deletion and reordering tasks, while speech and multi-modal combinations of select & speech are considered suitable for replacements and insertions. Overall, experiment participants were enthusiastic about the new modalities and saw them as useful extensions to mouse & keyboard, but not as a complete substitute.
In this paper we present an English–Hindi and Hindi–English neural machine translation (NMT) system, submitted to the Translation shared Task organized at WAT 2020. We trained a multilingual NMT system based on transformer architecture. In this paper we show: (i) how effective pre-processing helps to improve performance, (ii) how synthetic data through back-translation from available monolingual data can help in overall translation performance, (iii) how language similarity can aid more onto it. Our submissions ranked 1st in both English to Hindi and Hindi to English translation achieving BLEU 20.80 and 29.59 respectively.
This paper presents the results of the premier shared task organized alongside the Conference on Machine Translation (WMT) 2019. Participants were asked to build machine translation systems for any of 18 language pairs, to be evaluated on a test set of news stories. The main metric for this task is human judgment of translation quality. The task was also opened up to additional test suites to probe specific aspects of translation.
In this paper we describe our joint submission (JU-Saarland) from Jadavpur University and Saarland University in the WMT 2019 news translation shared task for English–Gujarati language pair within the translation task sub-track. Our baseline and primary submissions are built using Recurrent neural network (RNN) based neural machine translation (NMT) system which follows attention mechanism. Given the fact that the two languages belong to different language families and there is not enough parallel data for this language pair, building a high quality NMT system for this language pair is a difficult task. We produced synthetic data through back-translation from available monolingual data. We report the translation quality of our English–Gujarati and Gujarati–English NMT systems trained at word, byte-pair and character encoding levels where RNN at word level is considered as the baseline and used for comparison purpose. Our English–Gujarati system ranked in the second position in the shared task.
In this paper we present an English–German Automatic Post-Editing (APE) system called transference, submitted to the APE Task organized at WMT 2019. Our transference model is based on a multi-encoder transformer architecture. Unlike previous approaches, it (i) uses a transformer encoder block for src, (ii) followed by a transformer decoder block, but without masking, for self-attention on mt, which effectively acts as second encoder combining src –> mt, and (iii) feeds this representation into a final decoder block generating pe. Our model improves over the raw black-box neural machine translation system by 0.9 and 1.0 absolute BLEU points on the WMT 2019 APE development and test set. Our submission ranked 3rd, however compared to the two top systems, performance differences are not statistically significant.
In this paper we present the UDS-DFKI system submitted to the Similar Language Translation shared task at WMT 2019. The first edition of this shared task featured data from three pairs of similar languages: Czech and Polish, Hindi and Nepali, and Portuguese and Spanish. Participants could choose to participate in any of these three tracks and submit system outputs in any translation direction. We report the results obtained by our system in translating from Czech to Polish and comment on the impact of out-of-domain test data in the performance of our system. UDS-DFKI achieved competitive performance ranking second among ten teams in Czech to Polish translation.
In this paper, we propose different architectures for language independent machine transliteration which is extremely important for natural language processing (NLP) applications. Though a number of statistical models for transliteration have already been proposed in the past few decades, we proposed some neural network based deep learning architectures for the transliteration of named entities. Our transliteration systems adapt two different neural machine translation (NMT) frameworks: recurrent neural network and convolutional sequence to sequence based NMT. It is shown that our method provides quite satisfactory results when it comes to multi lingual machine transliteration. Our submitted runs are an ensemble of different transliteration systems for all the language pairs. In the NEWS 2018 Shared Task on Transliteration, our method achieves top performance for the En–Pe and Pe–En language pairs and comparable results for other cases.
In this paper we present a system based on SVM ensembles trained on characters and words to discriminate between five similar languages of the Indo-Aryan family: Hindi, Braj Bhasha, Awadhi, Bhojpuri, and Magahi. The system competed in the Indo-Aryan Language Identification (ILI) shared task organized within the VarDial Evaluation Campaign 2018. Our best entry in the competition, named ILIdentification, scored 88.95% F1 score and it was ranked 3rd out of 8 teams.
In this paper we present the first neural-based machine translation system trained to translate between standard national varieties of the same language. We take the pair Brazilian - European Portuguese as an example and compare the performance of this method to a phrase-based statistical machine translation system. We report a performance improvement of 0.9 BLEU points in translating from European to Brazilian Portuguese and 0.2 BLEU points when translating in the opposite direction. We also carried out a human evaluation experiment with native speakers of Brazilian Portuguese which indicates that humans prefer the output produced by the neural-based system in comparison to the statistical system.
The paper presents our participation in the WMT 2018 shared task on word level quality estimation (QE) of machine translated (MT) text, i.e., to predict whether a word in MT output for a given source context is correctly translated and hence should be retained in the post-edited translation (PE), or not. To perform the QE task, we measure the similarity of the source context of the target MT word with the context for which the word is retained in PE in the training data. This is achieved in two different ways, using Bag-of-Words (BoW) model and Document-to-Vector (Doc2Vec) model. In the BoW model, we compute the cosine similarity while in the Doc2Vec model we consider the Doc2Vec similarity. By applying the Kneedle algorithm on the F1mult vs. similarity score plot, we derive the threshold based on which OK/BAD decisions are taken for the MT words. Experimental results revealed that the Doc2Vec model performs better than the BoW model on the word level QE task.
This paper presents our English–German Automatic Post-Editing (APE) system submitted to the APE Task organized at WMT 2018 (Chatterjee et al., 2018). The proposed model is an extension of the transformer architecture: two separate self-attention-based encoders encode the machine translation output (mt) and the source (src), followed by a joint encoder that attends over a combination of these two encoded sequences (encsrc and encmt) for generating the post-edited sentence. We compare this multi-source architecture (i.e, {src, mt} → pe) to a monolingual transformer (i.e., mt → pe) model and an ensemble combining the multi-source {src, mt} → pe and single-source mt → pe models. For both the PBSMT and the NMT task, the ensemble yields the best results, followed by the multi-source model and last the single-source approach. Our best model, the ensemble, achieves a BLEU score of 66.16 and 74.22 for the PBSMT and NMT task, respectively.
We present a second-stage machine translation (MT) system based on a neural machine translation (NMT) approach to automatic post-editing (APE) that improves the translation quality provided by a first-stage MT system. Our APE system (APE_Sym) is an extended version of an attention based NMT model with bilingual symmetry employing bidirectional models, mt–pe and pe–mt. APE translations produced by our system show statistically significant improvements over the first-stage MT, phrase-based APE and the best reported score on the WMT 2016 APE dataset by a previous neural APE system. Re-ranking (APE_Rerank) of the n-best translations from the phrase-based APE and APE_Sym systems provides further substantial improvements over the symmetric neural APE model. Human evaluation confirms that the APE_Rerank generated PE translations improve on the previous best neural APE system at WMT 2016.
This paper presents CATaLog online, a new web-based MT and TM post-editing tool. CATaLog online is a freeware software that can be used through a web browser and it requires only a simple registration. The tool features a number of editing and log functions similar to the desktop version of CATaLog enhanced with several new features that we describe in detail in this paper. CATaLog online is designed to allow users to post-edit both translation memory segments as well as machine translation output. The tool provides a complete set of log information currently not available in most commercial CAT tools. Log information can be used both for project management purposes as well as for the study of the translation process and translator’s productivity.
In this paper we combine two strands of machine translation (MT) research: automatic post-editing (APE) and multi-engine (system combination) MT. APE systems learn a target-language-side second stage MT system from the data produced by human corrected output of a first stage MT system, to improve the output of the first stage MT in what is essentially a sequential MT system combination architecture. At the same time, there is a rich research literature on parallel MT system combination where the same input is fed to multiple engines and the best output is selected or smaller sections of the outputs are combined to obtain improved translation output. In the paper we show that parallel system combination in the APE stage of a sequential MT-APE combination yields substantial translation improvements both measured in terms of automatic evaluation metrics as well as in terms of productivity improvements measured in a post-editing experiment. We also show that system combination on the level of APE alignments yields further improvements. Overall our APE system yields statistically significant improvement of 5.9% relative BLEU over a strong baseline (English–Italian Google MT) and 21.76% productivity increase in a human post-editing experiment with professional translators.
We present a free web-based CAT tool called CATaLog Online which provides a novel and user-friendly online CAT environment for post-editors/translators. The goal is to support distributed translation, reduce post-editing time and effort, improve the post-editing experience and capture data for incremental MT/APE (automatic post-editing) and translation process research. The tool supports individual as well as batch mode file translation and provides translations from three engines – translation memory (TM), MT and APE. TM suggestions are color coded to accelerate the post-editing task. The users can integrate their personal TM/MT outputs. The tool remotely monitors and records post-editing activities generating an extensive range of post-editing logs.
Reordering poses a big challenge in statistical machine translation between distant language pairs. The paper presents how reordering between distant language pairs can be handled efficiently in phrase-based statistical machine translation. The problem of reordering between distant languages has been approached with prior reordering of the source text at chunk level to simulate the target language ordering. Prior reordering of the source chunks is performed in the present work by following the target word order suggested by word alignment. The testset is reordered using monolingual MT trained on source and reordered source. This approach of prior reordering of the source chunks was compared with pre-ordering of source words based on word alignments and the traditional approach of prior source reordering based on language-pair specific reordering rules. The effects of these reordering approaches were studied on an English–Bengali translation task, a language pair with different word order. From the experimental results it was found that word alignment based reordering of the source chunks is more effective than the other reordering approaches, and it produces statistically significant improvements over the baseline system on BLEU. On manual inspection we found significant improvements in terms of word alignments.