Thailand

Recent research in multilingual language models (LM) has demonstrated their ability to effectively handle multiple languages in a single model. This holds promise for low web-resource languages (LRL) as multilingual models can enable transfer of supervision from high resource languages to LRLs. However, incorporating a new language in an LM still remains a challenge, particularly for languages with limited corpora and in unseen scripts. In this paper we argue that relatedness among languages in a language family may be exploited to overcome some of the corpora limitations of LRLs, and propose RelateLM. We focus on Indian languages, and exploit relatedness along two dimensions: (1) script (since many Indic scripts originated from the Brahmic script), and (2) sentence structure. RelateLM uses transliteration to convert the unseen script of limited LRL text into the script of a Related Prominent Language (RPL) (Hindi in our case). While exploiting similar sentence structures, RelateLM utilizes readily available bilingual dictionaries to pseudo translate RPL text into LRL corpora. Experiments on multiple real-world benchmark datasets provide validation to our hypothesis that using a related language as pivot, along with transliteration and pseudo translation based data augmentation, can be an effective way to adapt LMs for LRLs, rather than direct training or pivoting through English.

ACL-IJCNLP 2021

Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study

alignment loss

pseudo-translation

transliteration

bert-based models

language families

relatedness

low web-resource languages

indic languages

natural language processing

**Welcome to ACL-IJCNLP 2021!**

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP). 

As in previous years, the program of the conference includes a poster session, tutorials, workshops and demonstrations in addition to the main conference.


We were able to keep the registration fees similar to those charged for the virtual ACL 2020. The one fee allows attendance at the main conference and any/all tutorials and workshops. These fees would be $125 Regular Early and $175 Regular Late; $50 Student Early and $75 Student Late. Early registration closes at midnight July 11, 2021 (Eastern Daylight Time).

**Reminder:** It is ACL’s policy that at least one author of each accepted paper (including ACL Finding papers) must register for the conference.

**Reminder2:** Underline site will open closer to the event. If you already registered you will receive access detail

Registration is now open

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP).

poster

Languages are dynamic systems: word usage may change over time, reflecting various societal factors. However, all languages do not evolve identically: the impact of an event, the influence of a trend or thinking, can differ between communities.
In this paper, we propose to track these divergences by comparing the evolution of a word and its translation across two languages. We investigate several methods of building time-varying and bilingual word embeddings, using contextualised and non-contextualised embeddings. We propose a set of scenarios to characterize semantic divergence across two languages, along with a setup to differentiate them in a bilingual corpus. We evaluate the different methods by generating a corpus of synthetic semantic change across two languages, English and French, before applying them to newspaper corpora to detect bilingual semantic divergence and provide qualitative insight for the task. We conclude that BERT embeddings coupled with a clustering step lead to the best performance on synthetic corpora; however, the performance of CBOW embeddings is very competitive and more adapted to an exploratory analysis on a large corpus.

Measure and Evaluation of Semantic Divergence across Two Languages

Multilingual neural machine translation has shown the capability of directly translating between language pairs unseen in training, i.e. zero-shot translation. Despite being conceptually attractive, it often suffers from low output quality. The difficulty of generalizing to new translation directions suggests the model representations are highly specific to those language pairs seen in training. We demonstrate that a main factor causing the language-specific representations is the positional correspondence to input tokens. We show that this can be easily alleviated by removing residual connections in an encoder layer. With this modification, we gain up to 18.5 BLEU points on zero-shot translation while retaining quality on supervised directions. The improvements are particularly prominent between related languages, where our proposed model outperforms pivot-based translation. Moreover, our approach allows easy integration of new languages, which substantially expands translation coverage. By thorough inspections of the hidden layer outputs, we show that our approach indeed leads to more language-independent representations.

Improving Zero-Shot Translation by Disentangling Positional Information

Commonsense reasoning research has so far been limited to English.
We aim to evaluate and improve popular multilingual language models (ML-LMs) to help advance commonsense reasoning (CSR) beyond English.
We collect the Mickey corpus, consisting of 561k sentences in 11 different languages, which
can be used for analyzing and improving ML-LMs.
We propose Mickey Probe, a language-general probing task for fairly evaluating the common sense of popular ML-LMs across different languages.
In addition, we also create two new datasets, X-CSQA and X-CODAH, by translating their English versions to 14 other languages, so that we can evaluate popular ML-LMs for cross-lingual commonsense reasoning.
To improve the performance beyond English, 
we propose a simple yet effective method --- multilingual contrastive pretraining (MCP).
It significantly enhances sentence representations, yielding a large performance gain on both benchmarks (e.g., +2.7% accuracy for X-CSQA over XLM-R_L).

Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense Reasoning

Attention mechanisms have achieved substantial improvements in neural machine translation by dynamically selecting relevant inputs for different predictions. However, recent studies have questioned the attention mechanisms' capability for discovering decisive inputs. In this paper, we propose to calibrate the attention weights by introducing a mask perturbation model that automatically evaluates each input's contribution to the model outputs. We increase the attention weights assigned to the indispensable tokens, whose removal leads to a dramatic performance decrease. The extensive experiments on the Transformer-based translation have demonstrated the effectiveness of our model. We further find that the calibrated attention weights are more uniform at lower layers to collect multiple information while more concentrated on the specific inputs at higher layers. Detailed analyses also show a great need for calibration in the attention weights with high entropy where the model is unconfident about its decision.

Attention Calibration for Transformer in Neural Machine Translation

Good quality monolingual word embeddings (MWEs) can be built for languages which have large amounts of unlabeled text. MWEs can be aligned to bilingual spaces using only a few thousand word translation pairs.
For low resource languages training MWEs monolingually results in MWEs of poor quality, and thus poor bilingual word embeddings (BWEs) as well.
This paper proposes a new approach for building BWEs in which the vector space of the high resource source language is used as a starting point for training an embedding space for the low resource target language. By using the source vectors as anchors the vector spaces are automatically aligned during training. 
We experiment on English-German, English-Hiligaynon and English-Macedonian.
We show that our approach results not only in improved BWEs and bilingual lexicon induction performance, but also in improved target language MWE quality as measured using monolingual word similarity.

Anchor-based Bilingual Word Embeddings for Low-Resource Languages

We propose a new architecture for adapting a sentence-level sequence-to-sequence transformer by incorporating multiple pre-trained document context signals and assess the impact on translation performance of (1) different pretraining approaches for generating these signals, (2) the quantity of parallel data for which document context is available, and (3) conditioning on source, target, or source and target contexts. Experiments on the NIST Chinese-English, and IWSLT and WMT English-German tasks support four general conclusions: that using pre-trained context representations markedly improves sample efficiency, that adequate parallel data resources are crucial for learning to use document context, that jointly conditioning on multiple context representations outperforms any single representation, and that source context is more valuable for translation performance than target side context. Our best multi-context model consistently outperforms the best existing context-aware transformers.

Diverse Pretrained Context Encodings Improve Document Translation

This paper investigates bounds on the generative capacity of prosodic processes, by focusing on the complexity of recursive prosody in coordination contexts in English (Wagner, 2010). Although all phonological processes and most prosodic processes are computationally regular string languages, we show that recursive prosody is not. The output string language is instead parallel multiple context-free (Seki et al., 1991). We evaluate the complexity of the pattern over strings, and then move on to a characterization over trees that requires the expressivity of multi bottom-up tree transducers. In doing so, we provide a foundation for future mathematically grounded investigations of the syntax-prosody interface.

Recursive prosody is not finite-state

Raimy (1999; 2000a; 2000b) proposed a graphical formalism for modeling reduplication, originallymostly focused on phonological overapplication in a derivational framework. This framework is now known as Precedence-based phonology or Multiprecedence phonology. Raimy's idea is that the segments at the input to the phonology are not totally ordered by precedence. This paper tackles a challenge that arose with Raimy's work, the development of a deterministic serialization algorithm as part of the derivation of surface forms. The Match-Extend algorithm introduced here requires fewer assumptions and sticks tighter to the attested typology. The algorithm also contains no parameter or constraint specific to individual graphs or topologies, unlike previous proposals. Match-Extend requires nothing except knowing the last added set of links.

The Match-Extend Serialization Algorithm in Multiprecedence

This paper investigates how abstract processes like suffixation can be learned from morphological inflection task data using an analogical memory-based framework. In this framework, the inflection target form is specified by providing an example inflection of another word in the language. This model is capable of near-baseline performance on the Sig-Morphon 2020 inflection challenge. Such a model can make predictions for unseen languages, allowing one-shot inflection for natural languages and the investigation of morphological transfer with synthetic probes. Accuracy for one-shot transfer can be unexpectedly high for some target languages (88% in Shona)and language families (53% across Romance). Probe experiments show that the model learns partially generalizable representations of prefixation, suffixation and reduplication, aiding its ability to transfer. The paper argues that the degree of generality of these process representations also helps to explain transfer results from previous research.

What transfers in morphological inflection? Experiments with analogical models

Total reduplication is common in natural language phonology and morphology. However, formally as copying on reduplicants of unbounded size, unrestricted total reduplication requires computational power beyond context-free, while other phonological and morphological patterns are regular, or even sub-regular. Thus, existing language classes characterizing reduplicated strings inevitably include typologically unattested context-free patterns, such as reversals. This paper extends regular languages to incorporate reduplication by introducing a new computational device: finite state buffered machine (FSBMs). We give its mathematical definitions and discuss some closure properties of the corresponding set of languages. As a result, the class of regular languages and languages derived from them through a copying mechanism is characterized. Suggested by previous literature, this class of languages should approach the characterization of natural language word sets.

Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study

Downloads

Next from ACL-IJCNLP 2021

Measure and Evaluation of Semantic Divergence across Two Languages

Similar lecture

Grammar-Constrained Neural Semantic Parsing with LR Parsers