Taiwan

Language models are pre-trained using large corpora of generic data like book corpus, common crawl and Wikipedia, which is essential for the model to understand the linguistic characteristics of the language. New studies suggest using Domain Adaptive Pre-training (DAPT) and Task-Adaptive Pre-training (TAPT) as an intermediate step before the final finetuning task. This step helps cover the target domain vocabulary and improves the model performance on the downstream task. In this work, we study the impact of training only the embedding layer on the model’s performance during TAPT and task-specific finetuning. Based on our study, we propose a simple approach to make the intermediate step of TAPT for BERT-based models more efficient by performing selective pretraining of BERT layers. We show that training only the BERT embedding layer during TAPT is sufficient to adapt to the vocabulary of the target domain and achieve comparable performance. Our approach is computationally efficient, with 78% fewer parameters trained during TAPT. The proposed embedding layer finetuning approach can also be an efficient domain adaptation technique.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-short.39/)

IJCNLP-AACL 2022

Towards Simple and Efficient Task-Adaptive Pre-training for Text Classification

language modelling

task adaptation

pretraining

### Welcome to ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics! 
 The conference will be held in Toronto, Canada, July 9-14, 2023. 
Following the succession of the recent conferences in our field, ACL 2023 will adopt a hybrid format.
While the impact of Covid has considerably diminished in terms of traveling, obtaining visas to Canada
entails a very long process. Moreover, the global economic conditions pose challenges for many individuals to travel to conferences. Recognizing these circumstances, we know many participants may not be
able to attend the conference in person. Therefore, we are committed to providing a great virtual platform
so everyone has the opportunity to interact with other participants and enjoy the conference. Based on the
current registered participants, approxiately 30% have chosen to attend the conference virtually. Whether
you join us in person or virtually, we sincerely hope everyone has a remarkable conference experience. 
This General Chair’s message is where I express my gratitude to the many individuals who have made
enormous contributions to the conference over the past year.

Read [**ACL 2023 General Chair's message**](https://docs.google.com/document/d/1WobYM7norbG4dI48s75HfJoD89qgX5a_F-6U8AteLSA/edit?usp=sharing/) in full.

##### **[Conference Handbook](https://2023.aclweb.org/downloads/acl2023-handbook.pdf)**

ACL 2023

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing.

poster

The AACL, Asia-Pacific Chapter of the Association for Computational Linguistics, and the AFNLP, Asian Federation of Natural Language Processing, invite you to participate in the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL) and the 10th International Joint Conference on Natural Language Processing (IJCNLP).

A registration is required to access this event. Access to the event site will be granted to all registered attendees on **November 16th**. If you have not already done so, please register using the link below:
 
 https://conference.iis.sinica.edu.tw/servlet/Register?ConferenceID=411

Registration Is Required

The AACL, Asia-Pacific Chapter of the Association for Computational Linguistics, and the AFNLP, Asian Federation of Natural Language Processing, invite you to participate in the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL) and the 10th International Joint Conference on Natural Language Processing (IJCNLP). 

Polysynthetic languages present a challenge for morphological analysis due to the complexity of their words and the lack of high-quality annotated datasets needed to build and/or evaluate computational models. The contribution of this work is twofold. First, using linguists’ help, we generate and contribute high-quality annotated data for two low-resource polysynthetic languages for two tasks: morphological segmentation and part-of-speech (POS) tagging. Second, we present the results of state-of-the-art unsupervised approaches for these two tasks on Adyghe and Inuktitut. Our findings show that for these polysynthetic languages, using linguistic priors helps the task of morphological segmentation and that using stems rather than words as the core unit of abstraction leads to superior performance on POS tagging.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-short.41/)

Towards Unsupervised Morphological Analysis of Polysynthetic Languages

A simple machine learning model of pluralisation as a linear regression problem minimising a p-adic metric substantially outperforms even the most robust of Euclidean-space regressors on languages in the Indo-European, Austronesian, Trans New-Guinea, Sino-Tibetan, Nilo-Saharan, Oto-Meanguean and Atlantic-Congo language families. There is insufficient evidence to support modelling distinct noun declensions as a p-adic neighbourhood even in Indo-European languages.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-short.4/)

Number Theory Meets Linguistics: Modelling Noun Morphology Across 1497 Languages Using 2-adic Metrics

Lifelong language learning seeks to have models continuously learn multiple tasks in a sequential order without suffering from catastrophic forgetting. State-of-the-art approaches rely on sparse experience replay as the primary approach to prevent forgetting. Experience replay usually adopts sampling methods for the memory population; however, the effect of the chosen sampling strategy on model performance has not yet been studied. In this paper, we investigate how relevant the selective memory population is in the lifelong learning process of text classification and question-answering tasks. We found that methods that randomly store a uniform number of samples from the entire data stream lead to high performances, especially for low memory size, which is consistent with computer vision studies.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-short.20/)

How Relevant is Selective Memory Population in Lifelong Language Learning?

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-short.31/)

Performance-Efficiency Trade-Offs in Adapting Language Models to Text Classification Tasks

Existing subword segmenters are either 1) frequency-based without semantics information or 2) neural-based but trained on parallel corpora. To address this, we present BERTSeg, an unsupervised neural subword segmenter for neural machine translation, which utilizes the contextualized semantic embeddings of words from characterBERT and maximizes the generation probability of subword segmentations. Furthermore, we propose a generation probability-based regularization method that enables BERTSeg to produce multiple segmentations for one word to improve the robustness of neural machine translation. Experimental results show that BERTSeg with regularization achieves up to 8 BLEU points improvement in 9 translation directions on ALT, IWSLT15 Vi->En, WMT16 Ro->En, and WMT15 Fi->En datasets compared with BPE. In addition, BERTSeg is efficient, needing up to 5 minutes for training.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-short.12/)

BERTSeg: BERT Based Unsupervised Subword Segmentation for Neural Machine Translation

Machine translation traditionally refers to translating from a single source language into a single target language. In recent years, the field has moved towards large neural models translating from or into many languages. As the input and output languages vary, the model must be correctly cued to translate into the correct target language. This is typically done by prefixing language tokens onto the source or target sequence. A single token’s content can denote the source language, target language, or language pair. The location and content of the prefix varies and many approaches exist without much justification towards one method or another. As guidance to researchers and directions for future work, we present a series of comprehensive experiments that show how the positioning and type of a target language prefix token affects translation performance. We show that source-side prefixes consistently improve performance. Further, we find that best language token content varies dependent on the supported language set.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-short.19/)

The Effects of Language Token Prefixing for Multilingual Machine Translation

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-short.1/)

Transfer Learning for Humor Detection by Twin Masked Yellow Muppets

We build a dual-way neural dictionary to retrieve words given definitions, and produce definitions for queried words. The model learns the two tasks simultaneously and handles unknown words via embeddings. It casts a word or a definition to the same representation space through a shared layer, then generates the other form in a multi-task fashion. Our method achieves promising automatic scores on previous benchmarks without extra resources. Human annotators prefer the model's outputs in both reference-less and reference-based evaluation, indicating its practicality. Analysis suggests that multiple objectives benefit learning.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-short.2/)

A Unified Model for Reverse Dictionary and Definition Modelling

Previous studies on neural linguistic steganography, except Ueoka et al. (2021), overlook the fact that the sender must detokenize cover texts to avoid arousing the eavesdropper’s suspicion. In this paper, we demonstrate that segmentation
ambiguity indeed causes occasional decoding failures at the receiver’s side. With the nearubiquity of subwords, this problem now affects any language. We propose simple tricks to overcome this problem, which are even applicable to languages without explicit word boundaries.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-short.15/)

Addressing Segmentation Ambiguity in Neural Linguistic Steganography

The Transformer Language Model is a powerful tool that has been shown to excel at various NLP tasks and has become the de-facto standard solution thanks to its versatility. In this study, we employ pre-trained transformer document embeddings in an Active Learning task to group samples with the same labels in the embedding space on domain-specific corpora. We find that the calculated class embeddings are not close to the respective samples and consequently do not partition the embedding space in a meaningful way. In addition, using the class embeddings as an Active Learning strategy yields reduced results compared to all baselines.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-short.45/)

Downloads

Next from IJCNLP-AACL 2022

Towards Unsupervised Morphological Analysis of Polysynthetic Languages

Similar lecture

Rethinking Semi-supervised Learning with Language Models