Spain

Traditional neural machine translation is limited to the topmost encoder layer’s context representation and cannot directly perceive the lower encoder layers. Existing solutions usually rely on the adjustment of network architecture, making the calculation more complicated or introducing additional structural restrictions. In this work, we propose layer-wise multi-view learning to solve this problem, circumventing the necessity to change the model structure. We regard each encoder layer’s off-the-shelf output, a by-product in layer-by-layer encoding, as the redundant view for the input sentence. In this way, in addition to the topmost encoder layer (referred to as the primary view), we also incorporate an intermediate encoder layer as the auxiliary view. We feed the two views to a partially shared decoder to maintain independent prediction. Consistency regularization based on KL divergence is used to encourage the two views to learn from each other. Extensive experimental results on five translation tasks show that our approach yields stable improvements over multiple strong baselines. As another bonus, our method is agnostic to network architectures and can maintain the same inference speed as the original model.

COLING 2020

Layer-Wise Multi-View Learning for Neural Machine Translation

multi-view learning

consistency regularization

neural machine translation

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

poster

This paper proposed a new subword segmentation method for neural machine translation, "Bilingual Subword Segmentation," which tokenizes sentences to minimize the difference between the number of subword units in a sentence and that of its translation.
While existing subword segmentation methods tokenize a sentence without considering its translation, the proposed method tokenizes a sentence by using subword units induced from bilingual sentences; this method could be more favorable to machine translation. 
Evaluations on WAT Asian Scientific Paper Excerpt Corpus (ASPEC) English-to-Japanese and Japanese-to-English translation tasks and WMT14 English-to-German and German-to-English translation tasks show that our bilingual subword segmentation improves the performance of Transformer neural machine translation (up to +0.81 BLEU). 


Bilingual Subword Segmentation for Neural Machine Translation

Epidemiologists study the global impact of the spread of viruses by considering information on the DNA sequence and structure of viruses, as well as relying on accurate metadata. Although accurate localized geographical data is critical for creating maps of the locations of viruses and their migration paths, most publicly available databases, such as GenBank, provide insufficient details on the matter, limited to country or state level. Therefore, a manual inspection of biomedical articles is vital for obtaining more detailed information about the locations of the viruses.

TIMBERT: Toponym Identifier For The Medical Domain Based on BERT

The lack of annotated data is a big issue for building reliable NLP systems for most of the world’slanguages. But this problem can be alleviated by automatic data generation. In this paper, wepresent a new data augmentation method for artificially creating new dependency-annotated sen-tences. The main idea is to swap subtrees between annotated sentences while enforcing strongconstraints on those trees to ensure maximal grammaticality of the new sentences. We also pro-pose a method to perform low-resource experiments using resource-rich languages by mimickinglow-resource languages by sampling sentences under a low-resource distribution. In a series ofexperiments, we show that our newly proposed data augmentation method outperforms previousproposals using the same basic inputs.

Data Augmentation via Subtree Swapping for Dependency Parsing of Low-Resource Languages

Emotion-cause pair extraction (ECPE) aims at extracting emotions and causes as pairs from documents, where each pair contains an emotion clause and a set of cause clauses. Existing approaches address the task by first extracting emotion and cause clauses via two binary classifiers separately, and then training another binary classifier to pair them up. However, the extracted emotion-cause pairs of different emotion types cannot be distinguished from each other through simple binary classifiers, which limits the applicability of the existing approaches. Moreover, such two-step approaches may suffer from possible cascading errors. In this paper, to address the first problem, we assign emotion type labels to emotion and cause clauses so that emotion- cause pairs of different emotion types can be easily distinguished. As for the second problem, we reformulate the ECPE task as a unified sequence labeling task, which can extract multiple emotion-cause pairs in an end-to-end fashion. We propose an approach composed of a convolution neural network for encoding neighboring information and two Bidirectional Long-Short Term Memory networks for two auxiliary tasks. Experiment results demonstrate the feasibility and effectiveness of our approaches.

A Unified Sequence Labeling Model for Emotion Cause Pair Extraction

A promising application of AI to healthcare is the retrieval of information from electronic health records (EHRs), e.g. to aid clinicians in finding relevant information for a consultation or to recruit suitable patients for a study.
This requires search capabilities far beyond simple string matching, including the retrieval of concepts (diagnoses, symptoms, medications, etc.) related to the one in question. 
The suitability of AI methods for such applications is tested by predicting the relatedness of concepts with known relatedness scores.
However, all existing biomedical concept relatedness datasets are notoriously small and consist of hand-picked concept pairs.
We open-source a novel concept relatedness benchmark overcoming these issues: it is six times larger than existing datasets 
and concept pairs are chosen based on co-occurrence in EHRs, ensuring their relevance for the application of interest.
We present an in-depth analysis of our new dataset and compare it to existing ones, highlighting that it is not only larger but also complements existing datasets in terms of the types of concepts included.
Initial experiments with state-of-the-art embedding methods show that our dataset is a challenging new benchmark for testing concept relatedness models.

Biomedical Concept Relatedness - A large EHR based benchmark

An essential task of most Question Answering (QA) systems is to re-rank the set of answer candidates, i.e., Answer Sentence Selection (AS2). These candidates are typically sentences either extracted from one or more documents preserving their natural order or retrieved by a search engine. Most state-of-the-art approaches to the task use huge neural models, such as BERT, or complex attentive architectures.
In this paper, we argue that by exploiting the intrinsic structure of the original rank together with an effective word-relatedness encoder, we achieve the highest accuracy among the cost-efficient models, with two orders of magnitude fewer parameters than the current state of the art. Our model takes 9.5 seconds to train on the WikiQA dataset, i.e., very fast in comparison with the 18 minutes required by a standard BERT-base fine-tuning.

A Study on Efficiency, Accuracy and Document Structure for Answer Sentence Selection

Sentence matching aims to identify the special relationship between two sentences, and plays a key role in many natural language processing tasks. However, previous studies mainly focused on exploiting either syntactic or semantic information for sentence matching, and no studies consider integrating both of them. In this study, we propose integrating syntax and semantics into BERT with sentence matching. In particular, we use an implicit syntax and semantics integration method that is less sensitive to the output structure information. Thus the implicit integration can alleviate the error propagation problem. The experimental results show that our approach has achieved state-of-the-art or competitive performance on several sentence matching datasets, demonstrating the benefits of implicitly integrating syntactic and semantic features in sentence matching.


Sentence Matching with Syntax- and Semantics-Aware BERT

We perform a corpus analysis to develop a representation of the knowledge and reasoning used to interpret indirect speech acts. An indirect speech act (ISA) is an utterance whose intended meaning is different from its literal meaning. We focus on those speech acts in which slight changes in situational or contextual information can switch the dominant intended meaning of an utterance from direct to indirect or vice-versa. We computationalize how various contextual features can influence a speaker’s beliefs, and how these beliefs can influence the intended meaning and choice of the surface form of an utterance. We axiomatize the domain-general patterns of reasoning involved, and implement a proof-of-concept architecture using Answer Set Programming. Our model is presented as a contribution to cognitive science and psycholinguistics, so representational decisions are justified by existing theoretical work.

Reasoning Requirements for Indirect Speech Acts

We reduce the model size of pre-trained word embeddings by a factor of $200$ while preserving its quality. Previous studies in this direction created a smaller word embedding model by reconstructing pre-trained word representations from those of subwords, which allows to store only a smaller number of subword embeddings in the memory. However, previous studies that train the reconstruction models using only target words cannot reduce the model size extremely while preserving its quality. Inspired by the observation of words with similar meanings having similar embeddings, our reconstruction training learns the global relationships among words, which can be employed in various models for word embedding reconstruction. Experimental results on word similarity benchmarks show that the proposed method improves the performance of the all subword-based reconstruction models.

Tiny Word Embeddings Using Globally Informed Reconstruction

Complex question answering (CQA) over raw text is a challenging task. A prominent approach to this task is based on the programmer-interpreter framework, where the programmer maps the question into a sequence of reasoning actions and the interpreter then executes these actions on the raw text. Learning an effective CQA model requires large amounts of human-annotated data, consisting of the ground-truth sequence of reasoning actions, which is time-consuming and expensive to collect at scale. In this paper, we address the challenge of learning a high-quality programmer (parser) by projecting natural human-generated questions into unnatural machinegenerated questions which are more convenient to parse. We firstly generate synthetic (question, action sequence) pairs by a data generator, and train a semantic parser that associates synthetic questions with their corresponding action sequences. To capture the diversity when applied to natural questions, we learn a projection model to map natural questions into their most similar unnatural questions for which the parser can work well. Without any natural training data, our projection model provides high-quality action sequences for the CQA task. Experimental results show that the QA model trained exclusively with synthetic data outperforms its state-of-the-art counterpart trained on human-labeled data.

Layer-Wise Multi-View Learning for Neural Machine Translation

Downloads

Next from COLING 2020

Bilingual Subword Segmentation for Neural Machine Translation

Similar lecture

Multilingual Neural Machine Translation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Layer-Wise Multi-View Learning for Neural Machine Translation

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from COLING 2020

Bilingual Subword Segmentation for Neural Machine Translation

Similar lecture

Multilingual Neural Machine Translation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads