Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
Evaluating zero-shot transfers and multilingual models for dependency parsing and POS tagging within the low-resource language family Tupían (2022.acl-srw)
Copied to clipboard
| Challenge: | Existing studies on NLP applications for low-resource languages have not been done in this area. |
| Approach: | They propose to replicate the transferability of dependency parsers and POS taggers trained on closely related languages within the low-resource language family Tupan. |
| Outcome: | The proposed models replicate the transferability of dependency parsers and POS taggers trained on closely related languages within the low-resource language family Tupan. |
RFBFN: A Relation-First Blank Filling Network for Joint Relational Triple Extraction (2022.acl-srw)
Copied to clipboard
| Challenge: | Existing methods for relational triple extraction ignore semantic information of relations or predict subjects and objects sequentially. |
| Approach: | They propose a relation-first blank filling network to capture semantic information of relations . they transform relations into relation templates with blanks which contain the fine-grained semantic representation of relations. |
| Outcome: | The proposed model outperforms current state-of-the-art methods on public benchmark datasets. |
Building a Dialogue Corpus Annotated with Expressed and Experienced Emotions (2022.acl-srw)
Copied to clipboard
| Challenge: | a human would recognize the emotion of an interlocutor and respond with an appropriate emotion, such as empathy and comfort. |
| Approach: | They propose to build a dialogue corpus annotated with two kinds of emotions . they collect tweets and annotate them with the emotion they put into the utterance . |
| Outcome: | The proposed method shows that it is difficult to recognize experienced emotions and multitask learning is effective. |
Darkness can not drive out darkness: Investigating Bias in Hate SpeechDetection Models (2022.acl-srw)
Copied to clipboard
| Challenge: | a recent study shows that machine learning models are biased and they might make the wrong decisions for the wrong reasons. |
| Approach: | They investigate the impact of social bias on the performance of hate speech detection models . they also investigate the causal effect of intersectional bias on models' unfairness . |
| Outcome: | The proposed model is biased and makes the wrong decisions for the wrong reasons. |
Ethical Considerations for Low-resourced Machine Translation (2022.acl-srw)
Copied to clipboard
| Challenge: | a paper examines the ethical implications of machine translation for low-resourced languages . a value scenario illustrates potential harms that low-rsourced language communities may face . |
| Approach: | They propose to use Armenian as a case study to investigate ethical implications of machine translation for low-resourced languages. |
| Outcome: | The proposed model is based on a value-scenario model of machine translation for low-resourced languages . the model is used to identify potential harms that low-income speakers may face . |
Integrating Question Rewrites in Conversational Question Answering: A Reinforcement Learning Approach (2022.acl-srw)
Copied to clipboard
| Challenge: | Existing approaches to improve QR performance dependencies among dialogue history dependencies are limited. |
| Approach: | They propose a reinforcement learning approach that integrates QR and CQA tasks without corresponding labeled QR datasets. |
| Outcome: | The proposed approach improves existing pipeline approaches in conversational question answering (QA) existing methods depend on assumption of corresponding QR datasets for every CQA dataset, resulting in poor performance. |
What Do You Mean by Relation Extraction? A Survey on Datasets and Study on Scientific Relation Classification (2022.acl-srw)
Copied to clipboard
| Challenge: | Existing RE surveys focus on modeling techniques, but there are few that are based on real-world scenarios. |
| Approach: | They propose to survey RE datasets and revisit the task definition and its adoption by the community. |
| Outcome: | The proposed approach improves the reliability of RE evaluations across multiple datasets and reveals significant discrepancies in annotations. |
Logical Inference for Counting on Semi-structured Tables (2022.acl-srw)
Copied to clipboard
| Challenge: | Natural Language Inference (NLI) tasks require numerical understanding to perform a numerical type of inference, such as counting. |
| Approach: | They propose a logical inference system for reasoning between semi-structured tables and texts that uses logical representations as meaning representations and model checking to handle a numerical type of inference. |
| Outcome: | The proposed system can perform inference with numerical comparatives with tables and texts in English. |
GNNer: Reducing Overlapping in Span-based NER Using Graph Neural Networks (2022.acl-srw)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) uses sequence labelling and span classification to identify entities. |
| Approach: | They propose a framework that uses Graph Neural Networks to enrich the span representation to reduce the number of overlapping spans during prediction. |
| Outcome: | The proposed framework reduces the number of overlapping spans while maintaining competitive metric performance. |
Compositional Semantics and Inference System for Temporal Order based on Japanese CCG (2022.acl-srw)
Copied to clipboard
| Challenge: | a system for temporal order in Japanese has not been developed for linguistic inference involving temporal expressions. |
| Approach: | They propose a Japanese NLI system that considers temporal order in Japanese . they use axioms for temporal relations and automated theorem provers to perform inference involving temporal orders. |
| Outcome: | The proposed system outperforms logic-based systems and current deep learning models on Japanese datasets. |
Combine to Describe: Evaluating Compositional Generalization in Image Captioning (2022.acl-srw)
Copied to clipboard
| Challenge: | Recent work on compositionality has focused on the ability to combine simpler concepts to understand & generate arbitrarily more complex conceptual structures. |
| Approach: | They propose to use a set of image captioning models to benchmark their compositional generalization properties. |
| Outcome: | The proposed models do not generalize in terms of systematicity and productivity, but are robust to synonym substitutions. |
Towards Unification of Discourse Annotation Frameworks (2022.acl-srw)
Copied to clipboard
| Challenge: | Discourse information is difficult to represent and annotate, and corpora annotated under different frameworks vary considerably. |
| Approach: | They propose to use automatic means to unify discourse structures and relations . they will also explore the application of the unified framework in multi-task learning and graphical models . |
| Outcome: | The proposed method can be used in multi-task learning and graphical models. |
AMR Alignment for Morphologically-rich and Pro-drop Languages (2022.acl-srw)
Copied to clipboard
| Challenge: | Existing AMR aligners for English are not well suited for many languages where many concepts appear from morphologically-semantic elements. |
| Approach: | They propose to use a tree traversal approach to align AMR concepts from morphemes in a Turkish language. |
| Outcome: | The proposed aligner outperforms the existing aligners for English and Portuguese in terms of precision, recall and F1 score. |
Sketching a Linguistically-Driven Reasoning Dialog Model for Social Talk (2022.acl-srw)
Copied to clipboard
| Challenge: | a new study shows that dialog systems that can hold social talk and make sense of conversational content are not efficient for context-sensitive natural language understanding and reasoning. |
| Approach: | They propose a linguistically-informed architecture to handle social talk in English . they propose linguistic models that fit the context-sensitive components into a Bayesian game-theoretic model . |
| Outcome: | The proposed architecture is based on corpus-based methods but does not track what is happening in a conversation. |
Scoping natural language processing in Indonesian and Malay for education applications (2022.acl-srw)
Copied to clipboard
| Challenge: | Limited natural language processing resources are available for Indonesian and Malay varieties and are difficult to locate. |
| Approach: | They propose to encourage collaboration and efficiency within NLP in Indonesian and Malay by identifying most published authors and research hubs. |
| Outcome: | The findings suggest that the field is dominated by exploratory corpus work, machine reading of text gathered from the Internet, and sentiment analysis. |
English-Malay Cross-Lingual Embedding Alignment using Bilingual Lexicon Augmentation (2022.acl-srw)
Copied to clipboard
| Challenge: | Embedings that are pre-trained monolingually are limited to tasks only in its own language. |
| Approach: | They propose to create English-Malay cross-lingual word embeddings using embedd alignment by exploiting existing language resources. |
| Outcome: | The proposed approach improves the quality of the existing English-Malay bilingual lexicon and the effect of Malay word coverage on the quality. |
Towards Detecting Political Bias in Hindi News Articles (2022.acl-srw)
Copied to clipboard
| Challenge: | Political propaganda in recent times has been amplified by media news portals through biased reporting, creating untruthful narratives on serious issues . a dataset for this task was not available, therefore we developed a transformer-based transfer learning method to fine-tune the pre-trained network on our data. |
| Approach: | They propose a transformer-based transfer learning method to fine-tune the pre-trained network on the data for this bias detection. |
| Outcome: | The proposed method fine-tunes the pre-trained network on the data to detect political bias in Hindi news articles. |
Restricted or Not: A General Training Framework for Neural Machine Translation (2022.acl-srw)
Copied to clipboard
| Challenge: | Existing work imposes constraints on beam search decoding, which limits the concurrent processing ability of the model in deployment. |
| Approach: | They propose a general training framework that allows a model to support both restricted and unrestricted translations by adopting an additional auxiliary training process without constraining the decoding process. |
| Outcome: | The proposed training framework is tested on simulated and original benchmarks. |
What do Models Learn From Training on More Than Text? Measuring Visual Commonsense Knowledge (2022.acl-srw)
Copied to clipboard
| Challenge: | Existing evaluation methods to measure what language models learn from multimodal training are lacking. |
| Approach: | They propose two evaluation tasks to measure commonsense knowledge in language models by using visual data to evaluate multimodal models and unimodal baselines. |
| Outcome: | The proposed evaluation tasks show that training on a visual modality improves on the visual commonsense knowledge in language models. |
TeluguNER: Leveraging Multi-Domain Named Entity Recognition with Deep Transformers (2022.acl-srw)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) is a successful and well-researched problem in English due to the availability of resources. |
| Approach: | They propose to use two annotated NER datasets for the Telugu language . they compare the finetuned Telugus model with the existing model in NER . |
| Outcome: | The proposed models outperform existing models on a large dataset of 38,363 sentences on telugu and other languages. |
Using Neural Machine Translation Methods for Sign Language Translation (2022.acl-srw)
Copied to clipboard
| Challenge: | Sign languages are the main medium of exchanging information for the deaf and hard of hearing. |
| Approach: | They propose to use two NMT architectures to train models on parallel German Sign Language corpora . they achieve substantial improvement in BLEU scores for the models trained on the two corporales . |
| Outcome: | The proposed models achieve significant improvements on the two corpora trained on the german sign language . the proposed models outperform the models trained on both corporales . |
Flexible Visual Grounding (2022.acl-srw)
Copied to clipboard
| Challenge: | Existing visual grounding datasets require queries to be answerable, but in multimedia data, many entities cannot be grounded to the image, resulting in unanswerable visual ground. |
| Approach: | They propose a method to ground to a pseudo image region for unanswerable queries . they add a query that cannot be grounded to the image and train it to ground . |
| Outcome: | The proposed model can handle answerable and unanswerable visual grounding with high accuracy on the proposed datasets. |
A large-scale computational study of content preservation measures for text style transfer and paraphrase generation (2022.acl-srw)
Copied to clipboard
| Challenge: | Text style transfer and paraphrases generation are growing areas of NLP . many researchers still use BLEU-like measures to evaluate content preservation . |
| Approach: | They compare 57 different measures based on different principles on 19 annotated datasets . they find that measures relying on cross-encoder models outperform alternative approaches . |
| Outcome: | The proposed methods outperform traditional methods on 19 datasets. |
Explicit Object Relation Alignment for Vision and Language Navigation (2022.acl-srw)
Copied to clipboard
| Challenge: | Existing work on vision and language navigation grounding the landmarks and spatial relations in textual instructions into visual modality is important. |
| Approach: | They propose a neural agent to explicitly align the spatial information in both instruction and visual environment, including landmarks and spatial relationships between the agent and landmarks. |
| Outcome: | The proposed method surpasses the baseline on the R2R dataset and shows that it can explain spatial reasoning and spatial relationships. |
Mining Logical Event Schemas From Pre-Trained Language Models (2022.acl-srw)
Copied to clipboard
| Challenge: | a pre-trained language model is induced into acting as a distribution over stories, a new system is proposed . NESL is a neural event schema learning system that combines large language models, FrameNet parsing, and simple behavioral schemas to bootstrap the learning process. |
| Approach: | They propose a neural event schema learning system that bootstraps the learning process by parsing pre-trained language models into simple behavioral schemas. |
| Outcome: | The proposed system combines large language models, a powerful logical representation of language, and simple behavioral schemas to bootstrap the learning process. |
Exploring Cross-lingual Text Detoxification with Large Multilingual Language Models. (2022.acl-srw)
Copied to clipboard
| Challenge: | Existing methods of textual style transfer are monolingual i.e. designed to work in one exact language. |
| Approach: | They propose to make large multilingual models capable of performing multilingual style transfer without direct fine-tuning in a given language. |
| Outcome: | The proposed model can generate text in a given language without fine-tuning and is able to perform cross-lingual detoxification without direct fine- tuning. |
MEKER: Memory Efficient Knowledge Embedding Representation for Link Prediction and Question Answering (2022.acl-srw)
Copied to clipboard
| Challenge: | Existing methods to embed learning use a standard Neural Networks (NN) backward mechanism, duplicating its memory consumption. |
| Approach: | They propose a memory-efficient KG embedding model that embeds knowledge graphs as 3rd-order binary tensors. |
| Outcome: | The proposed model yields comparable performance on link prediction and KG-based question answering tasks. |
Discourse on ASR Measurement: Introducing the ARPOCA Assessment Tool (2022.acl-srw)
Copied to clipboard
| Challenge: | Automated speech recognition (ASR) models are based on a corpus of audio recordings, but are often small or nonexistent for less common languages and dialects. |
| Approach: | This research proposal will develop a semi-automatic acoustic features extraction system that integrates phonetic transcripts with pronunciation dictionaries. |
| Outcome: | The proposed system will be used to improve language recognition and model feedback in less common languages and dialects. |
Pretrained Knowledge Base Embeddings for improved Sentential Relation Extraction (2022.acl-srw)
Copied to clipboard
| Challenge: | Existing models that perform explicit on-task training of graph embeddings are inadequate. |
| Approach: | They propose to combine pretrained knowledge base graph embeddings with transformer based language models to improve performance on sentential Relation Extraction task. |
| Outcome: | The proposed model outperforms state-of-the-art models on the sentential Relation Extraction task. |
Improving Cross-domain, Cross-lingual and Multi-modal Deception Detection (2022.acl-srw)
Copied to clipboard
| Challenge: | Deception detection is a deliberate choice to mislead to gain some advantage or avoid some penalty. |
| Approach: | They propose to use inter-domain distance to identify suitable source domain for a given target domain to improve cross-domain deception classification and to better understand multi-modal deception detection. |
| Outcome: | The proposed methods will be able to detect deception in cross-domain, cross-lingual and multi-modal settings and will improve multi-modular deception classification. |
Automatic Generation of Distractors for Fill-in-the-Blank Exercises with Round-Trip Neural Machine Translation (2022.acl-srw)
Copied to clipboard
| Challenge: | a fill-in-the-blank exercise involves removing one word from a sentence and generating distractors . a valid distractor is a word that does not fit the context, and distractors are invalid . |
| Approach: | They propose to automatically generate distractors using round-trip neural machine translation . they show that using hundreds of translations for a given sentence generates a rich set of distractors . |
| Outcome: | The proposed method outperforms two strong baselines against a real corpus of cloze exercises and manually checks for validity. |
On the Locality of Attention in Direct Speech Translation (2022.acl-srw)
Copied to clipboard
| Challenge: | Recent advances in NLP have created problems with the complexity of the self-attention layer. |
| Approach: | They propose to substitute standard self-attention with a local efficient one to avoid the computation of attention weights. |
| Outcome: | The proposed model matches the baseline performance and improves efficiency by skipping the computation of weights that standard attention discards. |
Extraction of Diagnostic Reasoning Relations for Clinical Knowledge Graphs (2022.acl-srw)
Copied to clipboard
| Challenge: | Existing methods for analyzing knowledge graphs focus on concept relations and clinical processes. |
| Approach: | They propose to extract clinical knowledge graphs from a wiki and consumer health resource texts by using a clinical reasoning ontology. |
| Outcome: | The proposed methods evaluate the correctness of extracted triples in the zero-shot setting. |
Scene-Text Aware Image and Text Retrieval with Dual-Encoder (2022.acl-srw)
Copied to clipboard
| Challenge: | Existing studies on image and text retrieval using a dual-encoder model have not shown their effectiveness for fast inferences. |
| Approach: | They propose a dual-encoder model that connects vision and language in the same semantic space and integrates scene-text and visual information into a model. |
| Outcome: | The proposed model can interpret scene-text and surrounding visual information better than cross-encoder models. |
Towards Fine-grained Classification of Climate Change related Social Media Text (2022.acl-srw)
Copied to clipboard
| Challenge: | a new study examines the fine-grained classification and classification of climate change-related social media text. |
| Approach: | They propose to use two datasets to analyze climate change-related social media text and propose a fine-grained classification based on the proposed dataset. |
| Outcome: | The proposed datasets are compared with existing datasets and benchmarked using the best-performing model. |
Deep Neural Representations for Multiword Expressions Detection (2022.acl-srw)
Copied to clipboard
| Challenge: | Existing methods for multiword expression detection are based on sequence labeling and statistical measures. |
| Approach: | They propose a weakly supervised method for multiword expressions extraction . they use a lexicon of English multiword lexical units as a reference knowledge base . |
| Outcome: | The proposed method can be easily applied to other languages. |
A Checkpoint on Multilingual Misogyny Identification (2022.acl-srw)
Copied to clipboard
| Challenge: | a study on hate speech against minorities in Italian tweets found that 1 women are the most targeted group. |
| Approach: | They propose to train monolingual transformers and multilingual transformer models with monolingual data in English, Italian, and Spanish to detect misogyny in tweets. |
| Outcome: | The proposed model achieves state-of-the-art on English, Italian, and Spanish. |
Using dependency parsing for few-shot learning in distributional semantics (2022.acl-srw)
Copied to clipboard
| Challenge: | Existing methods for few-shot learning use dependency parsing information to learn meaning of rare words based on limited amount of context sentences. |
| Approach: | They propose dependency parsing for few-shot learning to learn meaning of rare words . they use word embedding models as background spaces for few shot learning . |
| Outcome: | The proposed methods enhance the additive baseline model by using dependencies. |
A Dataset and BERT-based Models for Targeted Sentiment Analysis on Turkish Texts (2022.acl-srw)
Copied to clipboard
| Challenge: | Sentiment analysis is a field that is growing due to the availability of the Internet and the growing number of online platforms. |
| Approach: | They propose an annotated Turkish dataset suitable for targeted sentiment analysis. |
| Outcome: | The proposed models outperform the traditional models for the targeted sentiment analysis task. |