Korea, Republic of

Background: 
Fine-tuning the pre-trained language model (PrLM) on labeled sentiment datasets demonstrates impressive performance.


Problems: 
- collecting labeled sentiment dataset is time-consuming;
- updating the whole PrLM brings about much computation cost.

Our work:
We focus on the multi-source unsupervised sentiment adaptation task with the pre-trained features from PrLMs, which is more practical and challenging. There are two proposed modules for each above problem:
- dynamic feature network;
- asymmetric mutual learning.


COLING 2022

Asymmetric Mutual Learning for Multi-source Unsupervised Sentiment Adaptation with Dynamic Feature Network

multi-source unsupervised domain adaptation

sentiment analysis

pre-trained language model

[![](https://assets.underline.io/uploads/markdown_image/1/image/81a3c0317d24f663b49b996875024d45.png)](https://aclanthology.org/volumes/2022.coling-1/)



### THE CONFERENCE WE KNOW AND WE WANT.
**COLING**, the International Conference on Computational Linguistics, is one of the premier conferences for the natural language processing and computational linguistics.

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 including tech-startups. COLING provides opportunities for all these communities to showcase their exciting discovery.

In fall of 2022, COLING will be held in Gyeongju in a hybrid format. All participants can either present at the venue site or join virtually. As more people get vaccinated, we are happy to provide safer environments for our colleagues. We believe that COLING 2022 will be one of the conferences, free from the pandemic. The hybrid format gives presenters and sponsors a valuable opportunity to promote their companies in both an online and in-person venue. For the first time in a long time, customers can interact with their sponsor's products first-hand. The online venue, too, gives sponsors the chance to network with those unable to attend the in-person session.

The hybrid format ultimately lends itself to greater exposure for our sponsors: COLING2022 will let you reach more potential partners and customers than ever before!<br><br><br>

To gain access to this event page you are required to register.<br> Find more information and pay the registration fee on event the organizer’s website **[https://coling2022.org/reg](https://coling2022.org/reg)**

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for the natural language processing and computational linguistics.

poster

Bantu languages are spoken by communities in more than  half of the countries on the African continent by an estimated third of a billion people. Despite this populous and the amount of high quality linguistic research done over the years, Bantu languages are still computationally under-resourced. The biggest limitation to the development of computational methods for processing Bantu language text is their complex grammatical structure, chiefly in the system of noun classes. We investigated the use of a combined syntactic and semantic method to disambiguate among singular nouns with the same class prefix but belonging to different noun classes. This combination uses the semantic generalizations of the types of nouns in each class to overcome the limitations of relying only on the prefixes they take. We used  the nearest neighbors of a query word as semantic generalizations, and developed a tool to determine the noun class based on resources in Runyankore, a Bantu language indigenous to Uganda. We also investigated whether, with the same Runyankore resources, our method had utility in other Bantu languages, Luganda, indigenous to Uganda, and Kinyarwanda, indigenous to Rwanda. For all three languages, the combined approach resulted in an improvement in accuracy, as compared to using only the syntactic or the semantic approach.

Noun Class Disambiguation in Runyankore and Related Languages

A Zero-Shot Claim Detection Framework using Question Answering

Question answering (QA) has demonstrated impressive progress in answering questions from customized domains. Nevertheless, domain adaptation remains one of the most elusive challenges for QA systems, especially when QA systems are trained in a source domain but deployed in a different target domain. In this work, we investigate the potential benefits of question classification for QA domain adaptation. We propose a novel framework: Question Classification for Question Answering (QC4QA). Specifically, a question classifier is adopted to assign question classes to both the source and target data. Then, we perform joint training in a self-supervised fashion via pseudo-labeling. For optimization, inter-domain discrepancy between the source and target domain is reduced via maximum mean discrepancy (MMD) distance. We additionally minimize intra-class discrepancy among QA samples of the same question class for fine-grained adaptation performance. To the best of our knowledge, this is the first work in QA domain adaptation to leverage question classification with self-supervised adaptation. We demonstrate the effectiveness of the proposed QC4QA with consistent improvements against the state-of-the-art baselines on multiple datasets.

Domain Adaptation for Question Answering via Question Classification

MultiCoNER: A Large-scale Multilingual dataset for Complex Named Entity Recognition

Naturalness and expressiveness are crucial for audiobook speech synthesis, but now are limited by the averaged global-scale speaking style representation. In this paper, we propose an unsupervised multi-scale context-sensitive text-tospeech model for audiobooks. A multi-scale hierarchical context encoder is specially designed to predict both global-scale context style embedding and local-scale context style embedding from a wider context of input text in a hierarchical structure. Likewise, a multi-scale reference encoder is introduced to extract reference style embeddings at both global and local scales from the reference speech, which are used to guide the prediction of speaking styles. On top of these, a bi-reference attention mechanism is used to align both local-scale reference style embedding sequence and local-scale context style embedding sequence with corresponding phoneme embedding sequence. Both objective and subjective experiment results on a real-world multi-speaker Mandarin novel audio dataset demonstrate the excellent performance of our proposed method over all baselines in terms of naturalness and expressiveness of the synthesized speech.

Unsupervised Multi-scale Expressive Speaking Style Modeling with Hierarchical Context Information for Audiobook Speech Synthesis

Towards Better Semantic Understanding of Mobile Interfaces

The quality of Natural Language Processing (NLP) models is typically measured by the accuracy or error rate of a predefined test set. Because the evaluation and optimization of these measures are narrowed down to a specific domain like news and cannot be generalized to other domains like Twitter, we often observe that a system reported with human parity results generates surprising errors in real-life use scenarios. We address this weakness with a new approach that uses an NLP quality measure based on robustness. Unlike previous work that has defined robustness using Minimax to bound worst cases, we measure robustness based on the consistency of cross-domain accuracy and introduce the coefficient of variation and (epsilon, gamma)-Robustness. Our measures demonstrate higher agreements with human evaluation than accuracy scores like BLEU on ranking Machine Translation (MT) systems.

Measuring Robustness for NLP

Model explanations are crucial for the transparent, safe, and trustworthy deployment of machine learning models. The SHapley Additive exPlanations (SHAP) framework is considered by many to be a gold standard for local explanations thanks to its solid theoretical background and general applicability. In the years following
its publication, several variants appeared in the literature—presenting adaptations in the core assumptions and target applications. In this work, we review all relevant SHAP-based interpretability approaches available to date and provide instructive examples as well as recommendations regarding their applicability to NLP use
cases.


SHAP-Based Explanation Methods: A Review for NLP Interpretability

Target-oriented Opinion Words Extraction (TOWE) is a fine-grained sentiment analysis task that aims to extract the corresponding opinion words of a given opinion target from the sentence. Recently, deep learning approaches have made remarkable progress on this task. Nevertheless, the TOWE task still suffers from the scarcity of training data due to the expensive data annotation process. Limited labeled data increase the risk of distribution shift between test data and training data. In this paper, we propose exploiting massive unlabeled data to reduce the risk by increasing the exposure of the model to varying distribution shifts. Specifically, we propose a novel Multi-Grained Consistency Regularization (MGCR) method to make use of unlabeled data and design two filters specifically for TOWE to filter noisy data at different granularity. Extensive experimental results on four TOWE benchmark datasets indicate the superiority of MGCR compared with current state-of-the-art methods. The in-depth analysis also demonstrates the effectiveness of the different-granularity filters.

Exploiting Unlabeled Data for Target-Oriented Opinion Words Extraction

Some languages allow arguments to be omitted in certain contexts. Yet human language comprehenders reliably infer the intended referents of these zero pronouns, in part because they construct expectations about which referents are more likely. We ask whether Neural Language Models also extract the same expectations. We test whether 12 contemporary language models display expectations that reflect human behavior when exposed to sentences with zero pronouns from five behavioral experiments conducted in Italian by Carminati (2005). We find that three models—XGLM 2.9B, 4.5B, and 7.5B—capture the human behavior from all the experiments, with others successfully modeling some of the results. This result suggests that human expectations about coreference can be derived from exposure to language, and also indicates features of language models that allow them to better reflect human behavior.

Downloads

Next from COLING 2022

Noun Class Disambiguation in Runyankore and Related Languages

Similar lecture

BRCC and SentiBahasaRojak: The First Bahasa Rojak Corpus for Pretraining and Sentiment Analysis Dataset