Taiwan

Large pretrained multilingual models, trained on dozens of languages, have delivered promising results due to cross-lingual learning capabilities on a variety of language tasks. Further adapting these models to specific languages, especially ones unseen during pre-training, is an important goal toward expanding the coverage of language technologies. In this study, we show how we can use language phylogenetic information to improve cross-lingual transfer leveraging closely related languages \textit{in a structured, linguistically-informed manner}. We perform adapter-based training on languages from diverse language families (Germanic, Uralic, Tupian, Uto-Aztecan) and evaluate on both syntactic and semantic tasks, obtaining more than 20\% relative performance improvements over strong commonly used baselines, especially on languages unseen during pre-training.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.34/)

IJCNLP-AACL 2022

Phylogeny-Inspired Adaptation of Multilingual Models to New Languages

zero-shot-transfer

low-resource-language

multilinguality

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). 
<br>
<br>

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:
<br>
<br>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). 

technical paper

Neural metrics have achieved impressive correlation with human judgements in the evaluation of machine translation systems, but before we can safely optimise towards such metrics, we should be aware of (and ideally eliminate) biases toward bad translations that receive high scores. Our experiments show that sample-based Minimum Bayes Risk decoding can be used to explore and quantify such weaknesses. When applying this strategy to COMET for en-de and de-en, we find that COMET models are not sensitive enough to discrepancies in numbers and named entities. We further show that these biases are hard to fully remove by simply training on additional synthetic data and release our code and data for facilitating further experiments.

Identifying Weaknesses in Machine Translation Metrics Through Minimum Bayes Risk Decoding: A Case Study for COMET

Neural machine translation (NMT) models are known to be fragile to noisy inputs from automatic speech recognition (ASR) systems. Existing methods are usually tailored for robustness against only homophone errors which account for a small portion of realistic ASR errors. In this paper, we propose an adversarial example generation method based on confusion sets that contain words easily confusable with a target word by ASR to conduct adversarial training for NMT models. Specifically, an adversarial example is generated from the perspective of acoustic relations instead of the traditional uniform or unigram sampling from the confusion sets. Experiments on different test sets with hand-crafted and real-world noise demonstrate the effectiveness of our method over previous methods. Moreover, our approach can achieve improvements in the clean test set.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-short.28/)

Adversarially Improving NMT Robustness to ASR Errors with Confusion Sets

This paper presents Domain-Specific Sub-network (DoSS). It uses a set of masks obtained through pruning to define a sub-network for each domain and finetunes the sub-network parameters on domain data. This performs very closely and drastically reduces the number of parameters compared to finetuning the whole
network on each domain. Also a method to make masks unique per domain is proposed and shown to greatly improve the generalization to unseen domains. In our experiments on German to English machine translation, the proposed method outperforms the strong baseline of continue training on multi-domain (medical,
tech and religion) data by 1.47 BLEU points. Also continue training DoSS on new domain (legal) outperforms the multi-domain (medical, tech, religion, legal) baseline by 1.52 BLEU points.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-short.43/)

Domain Specific Sub-network for Multi-Domain Neural Machine Translation

Open-Domain Generative Question Answering has achieved impressive performance in English by combining document-level retrieval with answer generation. These approaches, which we refer to as GENQA, can generate complete sentences, effectively answering both factoid and non-factoid questions. In this paper, we extend GENQA to the multilingual and cross-lingual settings. For this purpose, we first introduce GEN-TYDIQA, an extension of the TyDiQA dataset with well-formed and complete answers for Arabic, Bengali, English, Japanese, and Russian. Based on GEN-TYDIQA, we design a cross-lingual generative model that produces full-sentence answers by exploiting passages written in multiple languages, including languages different from the question. Our cross-lingual generative system outperforms answer sentence selection baselines for all 5 languages and monolingual generative pipelines for three out of five languages studied.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.27/)

Cross-Lingual Open-Domain Question Answering with Answer Sentence Generation

Definition generation is a task that aims to generate a definition of a target word or phrase given a context. Recently, pre-trained transformer-based models have achieved great success in the task of definition generation (DG). However, previous encoder-decoder models lack effective representation learning to contain full semantic components of the given word, which leads to generating under-specific definitions. To address this problem, we propose a novel contrastive learning method, encouraging the model to capture more detailed semantic representations from the definition sequence encoding. According to both automatic and manual evaluation, the experimental results on three mainstream benchmarks demonstrate that the proposed method could generate more specific and high-quality definitions compared with several state-of-the-art models.

Fine-grained Contrastive Learning for Definition Generation

We propose a method for controlling the difficulty of a sentence based on deep reinforcement learning. Although existing models are trained based on the word-level difficulty, the sentence-level difficulty has not been taken into account in the loss function. Our proposed method generates sentences of appropriate difficulty for the target audience through reinforcement learning using a reward calculated based on the difference between the difficulty of the output sentence and the target difficulty. Experimental results of English text simplification show that the proposed method achieves a higher performance than existing approaches. Compared to previous studies, the proposed method can generate sentences whose grade-levels are closer to those of human references estimated using a fine-tuned pre-trained model.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-short.49/)

Controllable Text Simplification with Deep Reinforcement Learning

To solve Math Word Problems, human students leverage diverse reasoning logic that reaches different possible equation solutions. However, the mainstream sequence-to-sequence approach of automatic solvers aims to decode a fixed solution equation supervised by human annotation.
In this paper, we propose a controlled equation generation solver by leveraging a set of control codes to guide the model to consider certain reasoning logic and decode the corresponding equations expressions transformed from the human reference.
The empirical results suggest that our method universally improves the performance on single-unknown (Math23K) and multiple-unknown (DRAW1K, HMWP) benchmarks, with substantial improvements up to 13.2% accuracy on the challenging multiple-unknown datasets. Our code is available at https://github.com/yiyunya/CTRL-MWP.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-short.32/)

Seeking Diverse Reasoning Logic: Controlled Equation Expression Generation for Solving Math Word Problems

The Fractality of Sentiment Arcs for Literary Quality Assessment - the Case of Nobel Laureates

Natural language understanding (NLU) tasks are typically defined by creating an annotated dataset in which each utterance is encountered once. Such data does not resemble real-world natural language interactions in which certain utterances are encountered frequently, others rarely.  For deployed NLU systems, this is a vital problem, since the underlying machine learning (ML) models are often fine-tuned on typical NLU data, in which utterance frequency is never factored in, and then applied to real-world data with a very different distribution.  Such systems need to maintain interpretation consistency for the high-frequency (head) utterances, while also doing well on low-frequency (tail) utterances. We propose an alternative strategy that explicitly uses utterance frequency in training data to learn models that are more robust to unknown distributions. We present a methodology to simulate utterance usage in two public corpora and create two new corpora with head, body and tail segments. We evaluate several methods for joint intent classification and named entity recognition (referred to as IC-NER), and propose to use two domain generalization (DG) approaches that we adapt to sequence labeling task. The DG approaches demonstrate up to 7.02% relative improvement in semantic accuracy over baselines on the tail data.  We provide insights as to why the proposed approaches work and show that the reasons for the observed improvements do not align with those reported in previous work.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.1/)

Downloads

Next from IJCNLP-AACL 2022

Identifying Weaknesses in Machine Translation Metrics Through Minimum Bayes Risk Decoding: A Case Study for COMET

Similar lecture

Cross-lingual Few-Shot Learning on Unseen Languages

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.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 2022

Identifying Weaknesses in Machine Translation Metrics Through Minimum Bayes Risk Decoding: A Case Study for COMET

Similar lecture

Cross-lingual Few-Shot Learning on Unseen Languages

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads