Thailand

We propose a method for generating paraphrases of English questions that retain the original intent but use a different surface form. Our model combines a careful choice of training objective with a principled information bottleneck, to induce a latent encoding space that disentangles meaning and form. We train an encoder-decoder model to reconstruct a question from a paraphrase with the same meaning and an exemplar with the same surface form, leading to separated encoding spaces. We use a Vector-Quantized Variational Autoencoder to represent the surface form as a set of discrete latent variables, allowing us to use a classifier to select a different surface form at test time. Crucially, our method does not require access to an external source of target exemplars. Extensive experiments and a human evaluation show that we are able to generate paraphrases with a better tradeoff between semantic preservation and syntactic novelty compared to previous methods.

IJCNLP-AACL 2021

Factorising Meaning and Form for Intent-Preserving Paraphrasing

vqvae

paraphrasing

paraphrase generation

language generation

**Welcome to ACL-IJCNLP 2021!**

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP). 

As in previous years, the program of the conference includes a poster session, tutorials, workshops and demonstrations in addition to the main conference.


We were able to keep the registration fees similar to those charged for the virtual ACL 2020. The one fee allows attendance at the main conference and any/all tutorials and workshops. These fees would be $125 Regular Early and $175 Regular Late; $50 Student Early and $75 Student Late. Early registration closes at midnight July 11, 2021 (Eastern Daylight Time).

**Reminder:** It is ACL’s policy that at least one author of each accepted paper (including ACL Finding papers) must register for the conference.

**Reminder2:** Underline site will open closer to the event. If you already registered you will receive access detail

Registration is now open

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP).

poster

This survey builds an interdisciplinary picture of Argument Mining (AM), with a strong focus on its potential to address issues related to Social and Political Science. More specifically, we focus on AM challenges related to its applications to social media and in the multilingual domain, and then proceed to the widely debated notion of argument quality. We propose a novel definition of argument quality which is integrated with that of deliberative quality from the Social Science literature. Under our definition, the quality of a contribution needs to be assessed at multiple levels: the contribution itself, its preceding context, and the consequential effect on the development of the upcoming discourse. The latter has not received the deserved attention within the community. We finally define an application of AM for Social Good: (semi-)automatic moderation, a highly integrative application which (a) represents a challenging testbed for the integrated notion of quality we advocate, (b) allows the empirical quantification of argument/deliberative quality to benefit from the developments in other NLP fields (i.e. hate speech detection, fact checking, debiasing), and (c) has a clearly beneficial potential at the level of its societal thanks to its real-world application (even if extremely ambitious).

Towards Argument Mining for Social Good: A Survey

Research on the application of NLP in symbol-based Augmentative and Alternative Communication (AAC) tools for improving social interaction support is scarce. We contribute a novel method for generating context-related vocabulary from photographs of personally relevant events aimed at supporting people with language impairments in retelling their past experiences. Performance was calculated with information retrieval concepts on the relevance of vocabulary generated for communicating a corpus of 9730 narrative phrases about events depicted in 1946 photographs. In comparison to a baseline generation composed of frequent English words, our method generated vocabulary with a 4.6 gain in mean average precision, regardless of the level of contextual information in the input photographs, and 6.9 for photographs in which contextual information was extracted correctly. We conclude by discussing how our findings provide insights for system optimization and usage.

Automated Generation of Storytelling Vocabulary from Photographs for use in AAC

Continuity of care is crucial to ensuring positive health outcomes for patients discharged from an inpatient hospital setting, and improved information sharing can help. To share information, caregivers write discharge notes containing action items to share with patients and their future caregivers, but these action items are easily lost due to the lengthiness of the documents. In this work, we describe our creation of a dataset of clinical action items annotated over MIMIC-III, the largest publicly available dataset of real clinical notes. This dataset, which we call CLIP, is annotated by physicians and covers 718 documents representing 100K sentences. We describe the task of extracting the action items from these documents as multi-aspect extractive summarization, with each aspect representing a type of action to be taken. We evaluate several machine learning models on this task, and show that the best models exploit in-domain language model pre-training on 59K unannotated documents, and incorporate context from neighboring sentences. We also propose an approach to pre-training data selection that allows us to explore the trade-off between size and domain-specificity of pre-training datasets for this task.

CLIP: A Dataset for Extracting Action Items for Physicians from Hospital Discharge Notes

Emojis have become ubiquitous in digital communication, due to their visual appeal as well as their ability to vividly convey human emotion, among other factors. This also leads to an increased need for systems and tools to operate on text containing emojis. In this study, we assess this support by considering test sets of tweets with emojis, based on which we perform a series of experiments investigating the ability of prominent NLP and text processing tools to adequately process them. In particular, we consider tokenization, part-of-speech tagging, dependency parsing, as well as sentiment analysis. Our findings show that many systems still have notable shortcomings when operating on text containing emojis.

Assessing Emoji Use in Modern Text Processing Tools

Large-­scale morphological databases provide essential input to a wide range of NLP applica­tions. Inflectional data is of particular impor­tance for morphologically rich (agglutinative and highly inflecting) languages, and deriva­tions can be used, e.g. to infer the semantics of out­-of-­vocabulary words. Extending the scope of state-­of-­the-art multilingual morphological databases, we announce the release of Mor­phyNet, a high­-quality resource with 15 lan­guages, 519k derivational and 10.1M inflec­tional entries, and a rich set of morphologi­cal features. MorphyNet was extracted from Wiktionary using both hand­-crafted and auto­mated methods, and was manually evaluated to be of precision higher than 98%. Both the resource generation logic and the result­ing database are made freely available and are reusable as stand­alone tools or in combination with existing resources.

MorphyNet: a Large Multilingual Database of Derivational and Inflectional Morphology

Traditionally, character-level transduction problems have been solved with finite-state models designed to encode structural and linguistic knowledge of the underlying process, whereas recent approaches rely on the power and flexibility of sequence-to-sequence models with attention. Focusing on the less explored unsupervised learning scenario, we compare the two model classes side by side and find that they tend to make different types of errors even when achieving comparable performance. We analyze the distributions of different error classes using two unsupervised tasks as testbeds: converting informally romanized text into the native script of its language (for Russian, Arabic, and Kannada) and translating between a pair of closely related languages (Serbian and Bosnian). Finally, we investigate how combining finite-state and sequence-to-sequence models at decoding time affects the output quantitatively and qualitatively.

Comparative Error Analysis in Neural and Finite-state Models for Unsupervised Character-level Transduction

Shupamem, a language of Western Cameroon, is a tonal language which also exhibits the morpho-phonological process of full reduplication. This creates two challenges for a finite-state model of its morpho-syntax and morpho-phonology: how to manage the full reduplication, as well as the autosegmental nature of lexical tone. Dolatian and Heinz (2020) explain how 2-way finite-state transducers can model full reduplication without an exponential increase in states, and finite-state transducers with multiple tapes have been used to model autosegmental tiers, including tone (Wiebe, 1992; Dolatian and Rawski, 2020a;Rawski and Dolatian, 2020). Here we synthesize 2-way finite-state transducers and multi-tape transducers, resulting in a finite-state formalism that subsumes both, to account for the full reduplicative processes in Shupamem which also affect tone.

Finite-state Model of Shupamem Reduplication

Neural models excel at extracting statistical patterns from large amounts of data, but struggle to learn patterns or reason about language from only a few examples. In this work, we ask: Can we learn explicit rules that generalize well from only a few examples? We explore this question using program synthesis. We develop a synthesis model to learn phonology rules as programs in a domain-specific language. We test the ability of our models to generalize from few training examples using our new dataset of problems from the Linguistics Olympiad, a challenging set of tasks that require strong linguistic reasoning ability. In addition to being highly sample-efficient, our approach generates human-readable programs, and allows control over the generalizability of the learnt programs.

Sample-efficient Linguistic Generalizations through Program Synthesis: Experiments with Phonology Problems

Pronunciation lexicons and prediction models are a key component in several speech synthesis and recognition systems. We know that morphologically related words typically follow a fixed pattern of pronunciation which can be described by language-specific paradigms. In this work we explore how deep recurrent neural networks can be used to automatically learn and exploit this pattern to improve the pronunciation prediction quality of words related by morphological inflection. We propose two novel approaches for supplying morphological information, using the word's morphological class and its lemma, which are typically annotated in standard lexicons. We report improvements across a number of languages with varying degrees of phonological and morphological complexity, and two language families, with greater improvements for languages where the pronunciation prediction task is inherently more challenging. We also observe that combining bidirectional LSTM networks with attention mechanisms is an effective neural approach for the computational problem considered, across languages. Our approach seems particularly beneficial in the low resource setting, both by itself and in conjunction with transfer learning.

Morphology augmented pronunciation prediction

This tutorial targets researchers and practitioners who are interested in AI technologies that help machines understand natural language text, particularly real-world events described in the text. These include methods to extract the internal structures of an event regarding its protagonist(s), participant(s) and properties, as well as external structures concerning memberships, temporal and causal relations of multiple events. This tutorial will provide audience with a systematic introduction of (i) knowledge representations and acquisition of events, (ii) various methods for automated extraction, conceptualization, coreference resolution and prediction of events and their relations, (iii) induction of event processes and properties, and (iv) a wide range of NLP and commonsense understanding tasks that benefit from aforementioned techniques. We will conclude the tutorial by outlining emerging research problems in this area.

Factorising Meaning and Form for Intent-Preserving Paraphrasing

Downloads

Next from IJCNLP-AACL 2021

Towards Argument Mining for Social Good: A Survey

Similar lecture

Keep the Primary, Rewrite the Secondary: A Two-Stage Approach for Paraphrase Generation