Thailand

Providing example sentences that are diverse and aligned with learners&#39; proficiency levels is essential for fostering effective language acquisition. This study examines the use of Pre-trained Language Models (PLMs) to produce example sentences targeting L2 Japanese learners. We utilize PLMs in two ways: as quality scoring components in a retrieval system that draws from a newly curated corpus of Japanese sentences, and as direct sentence generators using zero-shot learning. We evaluate the quality of sentences by considering multiple aspects such as difficulty, diversity, and naturalness, with a panel of raters consisting of learners of Japanese, native speakers -- and GPT-4. Our findings suggest that there is inherent disagreement among participants on the ratings of sentence qualities, except for difficulty. Despite that, the retrieval approach was preferred by all evaluators, especially for beginner and advanced target proficiency, while the generative approaches received lower scores on average. Even so, our experiments highlight the potential for using PLMs to enhance the adaptability of sentence suggestion systems and therefore improve the language learning journey.

ACL 2024

Automatically Suggesting Diverse Example Sentences for L2 Japanese Learners Using Pre-Trained Language Models

example sentences

examples

language learning

retrieval

japanese

generation

Providing example sentences that are diverse and aligned with learners' proficiency levels is essential for fostering effective language acquisition. This study examines the use of Pre-trained Language Models (PLMs) to produce example sentences targeting L2 Japanese learners. We utilize PLMs in two ways: as quality scoring components in a retrieval system that draws from a newly curated corpus of Japanese sentences, and as direct sentence generators using zero-shot learning. We evaluate the quality of sentences by considering multiple aspects such as difficulty, diversity, and naturalness, with a panel of raters consisting of learners of Japanese, native speakers -- and GPT-4. Our findings suggest that there is inherent disagreement among participants on the ratings of sentence qualities, except for difficulty. Despite that, the retrieval approach was preferred by all evaluators, especially for beginner and advanced target proficiency, while the generative approaches received lower scores on average. Even so, our experiments highlight the potential for using PLMs to enhance the adaptability of sentence suggestion systems and therefore improve the language learning journey.

poster

### Welcome!
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. Our Virtual Poster Sessions will take place online Thursday, August 22, 2024.

You are required to register for this event. **Please register [here](https://2024.aclweb.org/registration). **

If you have already registered, please check your inbox for an email from Underline granting you access to ACL 2024 content.

Please register!

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. More information will be announced soon.

Coreference Resolution (CR) and Zero Pronoun Resolution (ZPR) are vital for extracting meaningful information from text. However, limited research and datasets pose significant challenges in Thai language. To address this, we developed an annotated joint CR and ZPR dataset. Additionally, we introduced the Z-coref model, capable of simultaneously handling CR and ZPR tasks by adjusting the span definition of a prior CR architecture to include token gaps. The proposed model trained on our dataset outperformed the state-of-the-art in resolving both coreference resolution and zero-pronoun resolution, while taking less time to train.

Z-coref: Thai Coreference and Zero Pronoun Resolution

Large Language Models (LLMs) have significant potential for facilitating intelligent end-user applications in healthcare. However, hallucinations remain an inherent problem with LLMs, making it crucial to address this issue with extensive medical knowledge and data. In this work, we propose a Retrieve-and-Medically-Augmented-Generation with Knowledge Reduction (ReMAG-KR) pipeline, employing a carefully curated knowledge base using cross-encoder re-ranking strategies. The pipeline is tested on medical MCQ-based QA datasets as well as general QA datasets. It was observed that when the knowledge base is reduced, the model's performance decreases by 2-8%, while the inference time improves by 47%.

ReMAG-KR: Retrieval and Medically Assisted Generation with Knowledge Reduction for Medical Question Answering

Retrieving relevant plots from the book for a query is a critical task, which can improve the reading experience and efficiency of readers. Readers usually only give an abstract and vague description as the query based on their own understanding, summaries, or speculations of the plot, which requires the retrieval model to have a strong ability to estimate the abstract semantic associations between the query and candidate plots. However, existing information retrieval (IR) datasets cannot reflect this ability well. In this paper, we propose PlotRetrieval, a labeled dataset to train and evaluate the performance of IR models on the novel task Plot Retrieval. Text pairs in PlotRetrieval have less word overlap and more abstract semantic association, which can reflect the ability of the IR models to estimate the abstract semantic association, rather than just traditional lexical or semantic matching. Extensive experiments across various lexical retrieval, sparse retrieval, dense retrieval, and cross-encoder methods compared with human studies on PlotRetrieval show current IR models still struggle in capturing abstract semantic association between texts. PlotRetrieval can be the benchmark for further research on the semantic association modeling ability of IR models.

Plot Retrieval as an Assessment of Abstract Semantic Association

Recent advancements in multilingual models for automatic speech recognition (ASR) have been able to achieve a high accuracy for languages with extremely limited resources. This study examines ASR modeling for the Mvskoke language, an indigenous language of America. The parameter efficiency of adapter training is contrasted with training entire models, and it is demonstrated how performance varies with different amounts of data. Additionally, the models are evaluated with trigram language model decoding, and the outputs are compared across different types of speech recordings. Results show that training an adapter is both parameter efficient and gives higher accuracy for a relatively small amount of data.

Fine-Tuning ASR models for Very Low-Resource Languages: A Study on Mvskoke

Prompt-based learning has shown its effectiveness in few-shot text classification. A key factor in its success is a verbalizer, which translates output from a language model into a predicted class. Notably, the simplest and widely acknowledged verbalizer employs manual labels to represent the classes. However, manual selection may not yield the optimal words for a given language model, potentially leading to subpar classification performance, especially in mid-to-low resource languages with weaker language models. Therefore, we propose Label-Aware Automatic Verbalizer (LAAV), effectively augmenting manual labels for improved few-shot classification results. Specifically, we utilize the label name along with the conjunction "and" to induce the model to generate more effective words for the verbalizer. Experimental results on four mid-to-low resource Southeast Asian languages demonstrate that LAAV significantly outperforms existing verbalizers.

Label-Aware Automatic Verbalizer for Few-Shot Text Classification in Mid-To-Low Resource Languages

Multiword Expressions (MWEs) make a good case study for linguistic diversity due to their idiosyncratic nature. Defining MWE canonical forms as types, may be measured notably through disparity, based on pairwise distances between types. To this aim, we train static MWE-aware word embeddings for verbal MWEs in 14 languages, and we show interesting properties of these vector spaces. Then use these vector spaces to implement the so-called functional diversity measure. We apply this measure to the results of several MWE identification systems. We find that, although MWE vector spaces are meaningful at a local scale, the disparity measure aggregating them at a global scale strongly correlates with the number of types, which questions its usefulness in presence of simpler diversity metrics such as variety. We make the vector spaces we generated available.

Vector Spaces for Quantifying Disparity of Multiword Expressions in Annotated Text

Any report frames issues to favor a particular interpretation by highlighting or excluding certain aspects of a story. Despite the widespread use of framing in disinformation, framing properties and detection methods remain underexplored outside the English-speaking world. We explore how multilingual framing of the same issue differs systematically. We use eight years of Russia-backed disinformation campaigns, spanning 8k news articles in 4 languages targeting 15 countries. We find that disinformation campaigns consistently and intentionally favor specific framing, depending on the target language of the audience. We further discover how Russian-language articles consistently highlight selected frames depending on the region of the media coverage. We find that the two most prominent models for automatic frame analysis underperform and show high disagreement, highlighting the need for further research.

Narratives at Conflict: Computational Analysis of News Framing in Multilingual Disinformation Campaigns

Vision-and-Language Navigation (VLN) encompasses interacting with autonomous vehicles using language and visual input from the perspective of mobility. Most of the previous work in this field focuses on spatial reasoning and the semantic grounding of visual information. However, reasoning based on the actions of pedestrians in the scene is not much considered. In this study, we provide a VLN dataset for destination prediction with action inference to investigate the extent to which current VLN models perform action inference. We introduce a crowd-sourcing process to construct a dataset for this task in two steps: (1) collecting beliefs about the next action for the user and (2) annotating the destination considering the user's next action. Our results on benchmarking using models working on destination prediction lead us to believe that although the models can learn to reason about the action and the next action to a certain extent, there is still much scope for improvement.

Action Inference for Destination Prediction in Vision-and-Language Navigation

In France, linguistic borrowings in the relatively conservative French language are an important site of cultural debate, and rap in particular is a hotspot for borrowings. In this work, we use computational methods to understand the factors that affect the prominence and prevalence of a borrowing. To do so, we manually annotate a lexicon of over 700 borrowings occurring in this context (including key aspects for each borrowing such as origin and semantic class). We analyze the prevalence of these borrowings in a newly collected corpus of over 8000 French rap song lyrics and find that there are increases in the proportion of linguistic borrowings, interjections, and Niger-Congo borrowings while terms related to the arts are decreasing in prevalence. Further research will include examining external factors (like song popularity) on the usage of words as well as machine learning methods to predict future lexical borrowing popularity trends.

A Computational Analysis and Exploration of Linguistic Borrowings in French Rap Lyrics

Large Language Models (LLMs) such as ChatGPT, GitHub Copilot, Llama, or Mistral assist programmers as copilots and knowledge sources to make the coding process faster and more efficient. This paper aims to improve the copilot performance by implementing different self-alignment processes and retrieval-augmented generation (RAG) pipelines, as well as their combination. To test the effectiveness of all approaches, we create a dataset and apply a model-based evaluation, using LLM as a judge. It is designed to check the model's abilities to understand the source code semantics, the dependency between files, and the overall meta-information about the repository. We also compare our approach with other existing solutions, e.g. ChatGPT-3.5, and evaluate on the existing benchmarks. Code and dataset are available online (https://anonymous.4open.science/r/ma_llm-382D).

Premium content

Automatically Suggesting Diverse Example Sentences for L2 Japanese Learners Using Pre-Trained Language Models

Next from ACL 2024

Z-coref: Thai Coreference and Zero Pronoun Resolution

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES