Thailand

The representation degeneration problem in Contextual Word Representations (CWRs) hurts the expressiveness of the embedding space by forming an anisotropic cone where even unrelated words have excessively positive correlations.
Existing techniques for tackling this issue require a learning process to re-train models with additional objectives and mostly employ a global assessment to study isotropy. 
Our quantitative analysis over isotropy shows that a local assessment could be more accurate due to the clustered structure of CWRs. 
Based on this observation, we propose a local cluster-based method to address the degeneration issue in contextual embedding spaces.
We show that in clusters including punctuations and stop words, local dominant directions encode structural information, removing which can improve CWRs performance on semantic tasks. 
Moreover, we find that tense information in verb representations dominates sense semantics. 
We show that removing dominant directions of verb representations can transform the space to better suit semantic applications. 
Our experiments demonstrate that the proposed cluster-based method can mitigate the degeneration problem on multiple tasks.

IJCNLP-AACL 2021

A Cluster-based Approach for Improving Isotropy in Contextual Embedding Space

representation degeneration problem

contextual embedding space

isotropy

**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).

technical paper

Subword segmentation algorithms have been a \textit{de facto} choice when building neural machine translation systems. However, most of them need to learn a segmentation model based on some heuristics, which may produce sub-optimal segmentation. This can be problematic in some scenarios when the target language has rich morphological changes or there is not enough data for learning compact composition rules.
Translating at fully character level has the potential to alleviate the issue, but empirical performances of character-based models has not been fully explored. 
In this paper, we present an in-depth comparison between character-based and subword-based NMT systems under three settings: translating to typologically diverse languages, training with low resource, and adapting to unseen domains. Experiment results show strong competitiveness of character-based models. Further analyses show that compared to subword-based models, character-based models are better at handling morphological phenomena, generating rare and unknown words, and more suitable for transferring to unseen domains.

When is Char Better Than Subword: A Systematic Study of Segmentation Algorithms for Neural Machine Translation

Analogies play a central role in human commonsense reasoning. The ability to recognize analogies such as “eye is to seeing what ear is to hearing”, sometimes referred to as analogical proportions, shape how we structure knowledge and understand language. Surprisingly, however, the task of identifying such analogies has not yet received much attention in the language model era. In this paper, we analyze the capabilities of transformer-based language models on this unsupervised task, using benchmarks obtained from educational settings, as well as more commonly used datasets. We find that off-the-shelf language models can identify analogies to a certain extent, but struggle with abstract and complex relations, and results are highly sensitive to model architecture and hyperparameters. Overall the best results were obtained with GPT-2 and RoBERTa, while configurations using BERT were not able to outperform word embedding models. Our results raise important questions for future work about how, and to what extent, pre-trained language models capture knowledge about abstract semantic relations.

BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?

We propose to measure fine-grained domain relevance– the degree that a term is relevant to a broad (e.g., computer science) or narrow (e.g., deep learning) domain. Such measurement is crucial for many downstream tasks in natural language processing. To handle long-tail terms, we build a core-anchored semantic graph, which uses core terms with rich description information to bridge the vast remaining fringe terms semantically. To support a fine-grained domain without relying on a matching corpus for supervision, we develop hierarchical core-fringe learning, which learns core and fringe terms jointly in a semi-supervised manner contextualized in the hierarchy of the domain. To reduce expensive human efforts, we employ automatic annotation and hierarchical positive-unlabeled learning. Our approach applies to big or small domains, covers head or tail terms, and requires little human effort. Extensive experiments demonstrate that our methods outperform strong baselines and even surpass professional human performance.

Measuring Fine-Grained Domain Relevance of Terms: A Hierarchical Core-Fringe Approach

Discrimination between antonyms and synonyms is an important and challenging NLP task. Antonyms and synonyms often share the same or similar contexts and thus are hard to make a distinction. This paper proposes two underlying hypotheses and employs the mixture-of-experts framework as a solution. It works on the basis of a divide-and-conquer strategy, where a number of localized experts focus on their own domains (or subspaces) to learn their specialties, and a gating mechanism determines the space partitioning and the expert mixture. Experimental results have shown that our method achieves the state-of-the-art performance on the task.

A Mixture-of-Experts Model for Antonym-Synonym Discrimination

Injecting external domain-specific knowledge (e.g., UMLS) into pretrained language models (LMs) advances their capability to handle specialised in-domain tasks such as biomedical entity linking (BEL). However, such abundant expert knowledge is available only for a handful of languages (e.g., English). In this work, by proposing a novel cross-lingual biomedical entity linking task (XL-BEL) and establishing a new XL-BEL benchmark spanning 10 typologically diverse languages, we first investigate the ability of standard knowledge-agnostic as well as knowledge-enhanced monolingual and multilingual LMs beyond the standard monolingual English BEL task. The scores indicate large gaps to English performance. We then address the challenge of transferring domain-specific knowledge in resource-rich languages to resource-poor ones. To this end, we propose and evaluate a series of cross-lingual transfer methods for the XL-BEL task, and demonstrate that general-domain bitext helps propagate the available English knowledge to languages with little to no in-domain data. Remarkably, we show that our proposed domain-specific transfer methods yield consistent gains across all target languages, sometimes up to 20 Precision@1 points, without any in-domain knowledge in the target language, and without any in-domain parallel data.

Learning Domain-Specialised Representations for Cross-Lingual Biomedical Entity Linking

Conversational Machine Reading (CMR) aims at answering questions in complicated interactive scenarios. Machine needs to answer questions through interactions with users based on given rule document, user scenario and dialogue history, and even initiatively asks questions for clarification if necessary. Namely, the answer to the task needs a machine in the response of either "Yes, No, Irrelevant" or to raise a follow-up question for further clarification. To effectively capture multiple objects in such a challenging task, graph modeling is supposed to be adopted, though it is surprising that this does not happen until this work proposes a dialogue graph modeling framework by incorporating two complementary graph models, i.e., explicit discourse graph and implicit discourse graph, which respectively capture explicit and implicit interactions hidden in the rule documents. The proposed model is evaluated on the ShARC benchmark and achieves new state-of-the-art by first exceeding the milestone accuracy score of 80%.

Dialogue Graph Modeling for Conversational Machine Reading

Indonesian language is heavily riddled with colloquialism whether in written or spoken forms. In this paper, we identify a class of Indonesian colloquial words that have undergone morphological transformations from their standard forms, categorize their word formations, and propose a benchmark dataset of Indonesian Colloquial Lexicons (IndoCollex) consisting of informal words on Twitter expertly annotated with their standard forms and their word formation types/tags. We evaluate several models for character-level transduction to perform morphological word normalization on this testbed to understand their failure cases and provide baselines for future work. As IndoCollex catalogues word formation phenomena that are also present in the non-standard text of other languages, it can also provide an attractive testbed for methods tailored for cross-lingual word normalization and non-standard word formation.

IndoCollex: A Testbed for Morphological Transformation of Indonesian Word Colloquialism

In this paper, we investigate few-shot joint
learning for dialogue language understanding.
Most existing few-shot models learn a single task each time with only a few examples. However, dialogue language understanding contains two closely related tasks, i.e., intent detection and slot filling, and often benefits from jointly learning the two tasks. This
calls for new few-shot learning techniques that
are able to capture task relations from only a
few examples and jointly learn multiple tasks.
To achieve this, we propose a similarity-based
few-shot learning scheme, named Contrastive
Prototype Merging network (ConProm), that
learns to bridge metric spaces of intent and
slot on data-rich domains, and then adapt the
bridged metric space to specific few-shot domain. Experiments on two public datasets,
Snips and FewJoint, show that our model significantly outperforms the strong baselines in
one and five shots settings.

Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling

Data augmentation with mixup has shown to be effective on various computer vision tasks. 
Despite its great success, there has been a hurdle to apply mixup to NLP tasks since text consists of discrete tokens with variable length. 
In this work, we propose SSMix, a novel mixup method where the operation is performed on input text rather than on hidden vectors like previous approaches.
SSMix synthesizes a sentence while preserving the locality of two original texts by span-based mixing and keeping more tokens related to the prediction relying on saliency information.
With extensive experiments, we empirically validate that our method outperforms hidden-level mixup methods on a wide range of text classification benchmarks, including textual entailment, sentiment classification, and question-type classification. 
Our code is available at https://github.com/clovaai/ssmix}{https://github.com/clovaai/ssmix.

SSMix: Saliency-Based Span Mixup for Text Classification

Language generation models' democratization benefits many domains, from answering health-related questions to enhancing education by providing AI-driven tutoring services. However, language generation models' democratization also makes it easier to generate human-like text at-scale for nefarious activities, from spreading misinformation to targeting specific groups with hate speech. Thus, it is essential to understand how people interact with bots and develop methods to detect bot-generated text. This paper shows that bot-generated text detection methods are more robust across datasets and models if we use information about how people respond to it rather than using the bot's text directly. We also analyze linguistic alignment, providing insight into differences between human-human and human-bot conversations.

A Cluster-based Approach for Improving Isotropy in Contextual Embedding Space

Downloads

Next from IJCNLP-AACL 2021

When is Char Better Than Subword: A Systematic Study of Segmentation Algorithms for Neural Machine Translation

Similar lecture

Two Parents, One Child: {D}ual Transfer for Low-Resource Neural Machine Translation

A Cluster-based Approach for Improving Isotropy in Contextual Embedding Space

.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 IJCNLP-AACL 2021

When is Char Better Than Subword: A Systematic Study of Segmentation Algorithms for Neural Machine Translation

Similar lecture

Two Parents, One Child: {D}ual Transfer for Low-Resource Neural Machine Translation

Downloads