Croatia

A major open problem in neural machine translation (NMT) is the translation of idiomatic expressions, such as &quot;under the weather&quot;. The meaning of these expressions is not composed by the meaning of their constituent words, and NMT models tend to translate them literally (i.e., word-by-word), which leads to confusing and nonsensical translations. Research on idioms in NMT is limited and obstructed by the absence of automatic methods for quantifying these errors. In this work, first, we propose a novel metric for automatically measuring the frequency of literal translation errors without human involvement. Equipped with this metric, we present controlled translation experiments with models trained in different conditions (with/without the test-set idioms) and across a wide range of (global and targeted) metrics and test sets. We explore the role of monolingual pretraining and find that it yields substantial targeted improvements, even without observing any translation examples of the test-set idioms. In our analysis, we probe the role of idiom context. We find that the randomly initialized models are more local or &quot;myopic&quot; as they are relatively unaffected by variations of the idiom context, unlike the pretrained ones.

EACL 2023

Automatic Evaluation and Analysis of Idioms in Neural Machine Translation

idioms

context

evaluation

analysis

machine translation

A major open problem in neural machine translation (NMT) is the translation of idiomatic expressions, such as "under the weather". The meaning of these expressions is not composed by the meaning of their constituent words, and NMT models tend to translate them literally (i.e., word-by-word), which leads to confusing and nonsensical translations. Research on idioms in NMT is limited and obstructed by the absence of automatic methods for quantifying these errors. In this work, first, we propose a novel metric for automatically measuring the frequency of literal translation errors without human involvement. Equipped with this metric, we present controlled translation experiments with models trained in different conditions (with/without the test-set idioms) and across a wide range of (global and targeted) metrics and test sets. We explore the role of monolingual pretraining and find that it yields substantial targeted improvements, even without observing any translation examples of the test-set idioms. In our analysis, we probe the role of idiom context. We find that the randomly initialized models are more local or "myopic" as they are relatively unaffected by variations of the idiom context, unlike the pretrained ones.

technical paper

### Welcome to the 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL) 
Continuing its mission of expanding and involving the science community of all European countries, EACL had selected the Ukrainian community for the 16th EACL, which took place online due to the COVID pandemic. Unfortunately, the ongoing war made the organisation in Kyiv impossible. Considering the importance of physical interaction among researchers, especially after the restrictions imposed by the COVID pandemic, in addition to an online mode, the conference will be held in Dubrovnik, Croatia, from 2 to 6 of May, 2023. The original aim of strengthening the connection with the Ukrainian community will not change as our program will feature a dedicated session and a workshop to highlight work on Ukrainian language technologies. As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language.

You need to register for the conference in order to access this site. Please visit https://2023.eacl.org/registration for more information.

As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language.

This work studies the semantic representations learned by BERT for compounds, that is, expressions such as sunlight or bodyguard. We build on recent studies that explore semantic information in Transformers at the word level and test whether BERT aligns with human semantic intuitions when dealing with expressions (e.g., sunlight) whose overall meaning depends—to a various extent—on the semantics of the constituent words (sun, light). We leverage a dataset that includes human judgments on two psycholinguistic measures of compound semantic analysis: lexeme meaning dominance (LMD; quantifying the weight of each constituent toward the compound meaning) and semantic transparency (ST; evaluating the extent to which the compound meaning is recoverable from the constituents' semantics). We show that BERT-based measures moderately align with human intuitions, especially when using contextualized representations, and that LMD is overall more predictable than ST. Contrary to the results reported for 'standard' words, higher, more contextualized layers are the best at representing compound meaning. These findings shed new light on the abilities of BERT in dealing with fine-grained semantic phenomena. Moreover, they can provide insights into how speakers represent compounds.

A Psycholinguistic Analysis of BERT's Representations of Compounds

Treebanks annotated with Universal Dependencies (UD) are currently available for over 100 languages and are widely utilized by the community. However, their inherent characteristics are hard to measure and are only partially reflected in parser evaluations via accuracy metrics like LAS. In this study, we analyze a large subset of the UD treebanks using three recently proposed accuracy-free dataset analysis methods: dataset cartography, \$\textbackslash{}mathcal\{V\}\$-information, and minimum description length. Each method provides insights about UD treebanks that would remain undetected if only LAS was considered. Specifically, we identify a number of treebanks that, despite yielding high LAS, contain very little information that is usable by a parser to surpass what can be achieved by simple heuristics. Furthermore, we make note of several treebanks that score consistently low across numerous metrics, indicating a high degree of noise or annotation inconsistency present therein.

Investigating UD Treebanks via Dataset Difficulty Measures

Representation of coreferential relations is a challenging and actively studied topic for pro-drop and morphologically rich languages (PD-MRLs) due to dropped pronouns (e.g., null subjects and omitted possessive pronouns). These phenomena require a representation scheme at the morphology level and enhanced evaluation methods. In this paper, we propose a representation \& evaluation scheme to incorporate dropped pronouns into coreference resolution and validate it on the Turkish language. Using the scheme, we extend the annotations on the only existing Turkish coreference dataset, which originally did not contain annotations for dropped pronouns. We provide publicly available pre and post processors to enhance the prominent CoNLL coreference scorer also to cover coreferential relations arising from dropped pronouns. As a final step, the paper reports the first neural Turkish coreference resolution results in the literature. Although validated on Turkish, the proposed scheme is language-independent and may be used for other PD-MRLs.

Incorporating Dropped Pronouns into Coreference Resolution: The case for Turkish

Automatic code generation from natural language descriptions can be highly beneficial during the process of software development. In this work, we propose GAP-Gen, a Guided Automatic Python Code Generation method based on Python syntactic constraints and semantic constraints. We first introduce Python
syntactic constraints in the form of Syntax-Flow, which is a simplified version of Abstract Syntax Tree (AST) reducing the size and high complexity of real Python AST but maintaining crucial syntactic information of Python code. In addition to Syntax-Flow, we introduce Variable-Flow which abstracts variable and function names consistently throughout the code. In our work, rather than pertaining, we focus on modifying the fine-tuning process which reduces computational requirements but retains high generation performance on automatic Python code generation task. GAP-Gen fine-tunes the transformer-based language models T5 and CodeT5 using
the Code-to-Docstring datasets CodeSearchNet, CodeSearchNet AdvTest and Code-Docstring-Corpus from EdinburghNLP. Our experiments show that GAP-Gen achieves better results on automatic Python code generation task than previous
works.

GAP-Gen: Guided Automatic Python Code Generation

Recent task-oriented dialogue systems are trained on annotated dialogues, which, in turn, reflect certain domain information (e.g., restaurants or hotels in a given region). However, when such domain knowledge changes (e.g., new restaurants open), the initial dialogue model may become obsolete, decreasing the overall performance of the system. Through a number of experiments, we show, for instance, that adding 50% of new slot-values reduces of about 55% the dialogue state-tracker performance. In light of such evidence, we suggest that automatic adaptation of training dialogues is a valuable option for re-training obsolete models. We experimented with a dialogue adaptation approach based on fine-tuning a generative language model on domain changes, showing that a significant reduction of performance decrease can be obtained.

Addressing Domain Changes in Task-oriented Conversational Agents through Dialogue Adaptation

Dealing with humor is an important step to develop Natural Language Processing tools capable of handling sophisticated semantic and pragmatic knowledge. In this context, this PhD thesis focuses on the automatic generation and recognition of verbal punning humor in Portuguese, which is still an underdeveloped language when compared to English. One of the main goals of this research is to conciliate Natural Language Generation computational models with existing theories of humor from the Humanities while avoiding mere generation by including contextual information into the generation process. Another point that is of utmost importance is the inclusion of the listener as an active part in the process of understanding and creating humor; we hope to achieve this by using concepts from Recommender Systems in our methods. Ultimately, we want to not only advance the current state-of-the-art in humor generation and recognition, but also to help the general Portuguese-speaking research community with methods, tools and resources that may aid in the development of further techniques for this language. We also expect our systems to provide insightful ideas about how humor is created and perceived by both humans and machines.

Towards Generation and Recognition of Humorous Texts in Portuguese

Citation screening is an essential yet time-consuming step of the systematic review process. Screening automation using machine learning techniques can speed up constructing a systematic review. Current efforts in automation are limited in their capabilities as they either only suggest the decisions or require large annotated datasets before making the predictions. In this PhD thesis, we propose several approaches to improving the screening automation techniques to reduce reviewers' work. First, we want to propose a unified benchmarking method for the citation screening task. We will then explore different machine learning algorithms for conducting screening, focusing on using fewer annotated examples to maintain stable results across multiple reviews. Next, we intend to experiment with using external information coming from eligibility criteria sheets as a substitute for manual annotations. Finally, we would like to assess our approaches to literature reviews outside of the medical domain.

Rapid Systematic Reviews: Zero-shot Citation Screening with the Usage of Eligibility Criteria

Examining a sample of Instant Messaging (IM) dialogues by conventional, manual methods, often used in social sciences, is difficult and inefficient for two reasons: a sample of significant size comprises a large quantity of unstructured text, and additionally, the occurrence of researched phenomena tends to be low. Therefore, automatic detection of particular psychological phenomena would enable the research of such data sources on a much larger scale than before. It will be the primary goal of the dissertation thesis to explore the possible Natural Language Processing (NLP) approaches to the problem and report their effectiveness. This proposal provides the theoretical basis by researching state-of-the-art solutions for related tasks, formulates hypotheses for the possible solutions, and presents the already achieved results. The proposed hypotheses will be verified in the dissertation thesis by designing, training, and evaluating predictive models. The resulting work will provide a comprehensive overview of different methods and their effectiveness. To the best of the author's knowledge, this thesis will be the first work to do so in this area on real IM dialogues provided by adolescents. The results could be used, for example, in parental applications, mental health applications that supervise users' well-being, risky online behavior detection, intent detection for chatbots, and many others. This proposal also describes a research plan for conducting the research and publishing the results.

Detecting Psychological Phenomena in Dialogues

Clinical natural language processing aims to tackle language and prediction tasks using text from medical practice, such as clinical notes, prescriptions, and discharge summaries. Several approaches have been tried to deal with these tasks. Since 2017, pre-trained language models (PLMs) have achieved state-of-the-art performance in many tasks. However, most works have been developed in English. This PhD research proposal addresses the development of PLMs for clinical NLP in Spanish. To carry out this study, we will build a clinical corpus big enough to implement a functional PLM. We will test several PLM architectures and evaluate them with language and prediction tasks. The novelty of this work lies in the use of only clinical text, while previous clinical PLMs have used a mix of general, biomedical, and clinical text.

Development of pre-trained language models for clinical NLP in Spanish

Generating polite responses is essential to build intelligent and engaging dialogue systems. However, this task is far from well-explored due to the difficulties of rendering a particular style in coherent responses, especially when parallel datasets for regular-to-polite pairs are usually unavailable. This paper proposes a polite chatbot that can produce responses that are polite and coherent to the given context. In this study, a politeness transfer model is first used to generate polite synthetic dialogue pairs of contexts and polite utterances. Then, these synthetic pairs are employed to train a dialogue model. Automatic and human evaluations demonstrate that our method outperforms baselines in producing polite dialogue responses while staying competitive in terms of coherent to the given context.

Premium content

Automatic Evaluation and Analysis of Idioms in Neural Machine Translation

Downloads

Next from EACL 2023

A Psycholinguistic Analysis of BERT's Representations of Compounds

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES