Spain

Due to the compelling improvements brought by BERT, many recent representation models adopted the Transformer architecture as their main building block, consequently inheriting the wordpiece tokenization system despite it not being intrinsically linked to the notion of Transformers. While this system is thought to achieve a good balance between the flexibility of characters and the efficiency of full words, using predefined wordpiece vocabularies from the general domain is not always suitable, especially when building models for specialized domains (e.g., the medical domain). Moreover, adopting a wordpiece tokenization shifts the focus from the word level to the subword level, making the models conceptually more complex and arguably less convenient in practice. For these reasons, we propose CharacterBERT, a new variant of BERT that drops the wordpiece system altogether and uses a Character-CNN module instead to represent entire words by consulting their characters. We show that this new model improves the performance of BERT on a variety of medical domain tasks while at the same time producing robust, word-level, and open-vocabulary representations.

COLING 2020

CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters

word-level

open-vocabulary

specialized domain

medical domain

character-level

elmo

language model

word embeddings

biomedical

clinical

bert

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

poster

In this paper we present a character-level sequence-to-sequence lemmatization model, utilizing several subword features in multiple configurations. In addition to generic n-gram embeddings (using FastText), we experiment with concatenative (stems) and templatic (roots and patterns) morphological subwords. We present several architectures that embed these features directly at the encoder side, or learn them jointly at the decoder side with a multitask learning architecture. The results indicate that using the generic n-gram embeddings (through FastText) outperform the other linguistically-driven subwords. We use Modern Standard Arabic and Egyptian Arabic as test cases, with up to 22% and 13% relative error reduction, respectively, from a strong baseline. An error analysis shows that our best system is even able to handle word/lemma pairs that are both unseen in the training data.

Utilizing Subword Entitiesin Character-Level Sequence-to-Sequence Lemmatization Models

Emotion analysis in polarized contexts represents a challenge for Natural Language Processing modeling. As a step in the aforementioned direction, we present a methodology to extend the task of Aspect-based Sentiment Analysis (ABSA) toward the affect and emotion representation in polarized settings. In particular, we adopt the three-dimensional model of affect based on Valence, Arousal, and Dominance (VAD). We then present a Brexit scenario that proves how affect varies toward the same aspect when politically polarized stances are presented. Our approach captures aspect-based polarization from newspapers regarding the Brexit scenario of 1.2m entities at sentence-level. We demonstrate how basic constituents of emotions can be mapped to the VAD model, along with their interactions respecting the polarized context in ABSA settings using biased key-concepts (e.g., “stop Brexit” vs. “support Brexit”). Quite intriguingly, the framework achieves to produce coherent aspect evidences of Brexit’s stance from key-concepts, showing that VAD influence the support and opposition aspects.

Regrexit or not Regrexit: Aspect-based Sentiment Analysis in Polarized Contexts

Automatic sarcasm detection from text is an important classification task that can help identify the actual sentiment in user-generated data, such as reviews or tweets. Despite its usefulness, sarcasm detection remains a challenging task, due to a lack of any vocal intonation or facial gestures in textual data. To date, most of the approaches to addressing the problem have relied on hand-crafted affect features, or pre-trained models of non-contextual word embeddings, such asWord2vec. However, these models inherit limitations that render them inadequate for the task of sarcasm detection. In this paper, we propose two novel deep neural network models for sarcasm detection, namely ACE 1 and ACE 2. Given as input a text passage, the models predict whether itis sarcastic (or not). Our models extend the architecture of BERT by incorporating both affective and contextual features. To the best of our knowledge, this is the first attempt to directly alterBERT’s architecture and train it from scratch to build a sarcasm classifier. Extensive experiments on different datasets demonstrate that the proposed models outperform state-of-the-art models for sarcasm detection with significant margins.

Affective and Contextual Embedding for Sarcasm Detection

Textual style transfer is a Natural Language Generation task which involves modifying the style of a text while keeping its content-related information.
It assumes that style and content are separable. Here, we employ unsupervised adversarial style transfer frameworks and frame the task as a multi-objective problem, balancing style shift with content preservation and fluency.
Also, we investigate the assumption of style content separation by studying how these models encode style-related features in their latent spaces by using a probing methodology and reinforcing technique.

Style versus Content: A distinction without a (learnable) difference?

Bilingual dictionary induction (BDI) is the task of accurately translating words to the target language. It is of great importance in many low-resource scenarios where cross-lingual training data is not available. To perform BDI, bilingual word embeddings (BWEs) are often used due to their low bilingual training signal requirements. They achieve high performance, but problematic cases still remain, such as the translation of rare words or named entities, which often need to be transliterated. In this paper, we enrich BWE-based BDI with transliteration information by using Bilingual Orthography Embeddings (BOEs). BOEs represent source and target language transliteration word pairs with similar vectors. A key problem in our BDI setup is to decide which information source – BWEs (or semantics) vs. BOEs (or orthography) – is more reliable for a particular word pair. We propose a novel classification-based BDI system that uses BWEs, BOEs and a number of other features to make this decision. We test our system on English-Russian BDI and show improved performance. In addition, we show the effectiveness of our BOEs by successfully using them for transliteration mining based on cosine similarity.

Combining Word Embeddings with Bilingual Orthography Embeddings for Bilingual Dictionary Induction

We set out to uncover the unique grammatical properties of an important yet so far under-researched type of natural language text: that of short labels typically found within structured datasets. We show that such labels obey a specific type of abbreviated grammar that we call the Language of Data, with properties significantly different from the kinds of text typically addressed in computational linguistics and NLP, such as ‘standard’ written language or social media messages. We analyse orthography, parts of speech, and syntax over a large, bilingual, hand-annotated corpus of data labels collected from a variety of domains. We perform experiments on tokenisation, part-of-speech tagging, and named entity recognition over real-world structured data, demonstrating that models adapted to the Language of Data outperform those trained on standard text. These observations point in a new direction to be explored as future research, in order to develop new NLP tools and models dedicated to the Language of Data.

Exploring the Language of Data

Gesture typing is a method of typing words on a touch-based keyboard by creating a continuous trace passing through the relevant keys. This work is aimed at developing a keyboard that supports gesture typing in Indic languages. We begin by noting that when dealing with Indic languages, one needs to cater to two different sets of users: (i) users who prefer to type in the native Indic script (Devanagari, Bengali, etc.) and (ii) users who prefer to type in the English script but want the transliterated output in the native script. In both cases, we need a model that takes a trace as input and maps it to the intended word. To enable the development of these models, we create and release two datasets. First, we create a dataset containing keyboard traces for 193,658 words from 7 Indic languages. Second, we curate 104,412 English-Indic transliteration pairs from Wikidata across these languages. Using these datasets we build a model that performs path decoding, transliteration and transliteration correction. Unlike prior approaches, our proposed model does not make co-character independence assumptions during decoding. The overall accuracy of our model across the 7 languages varies from 70-95%.

Joint Transformer/RNN Architecture for Gesture Typing in Indic Languages

Unsupervised neural machine translation (NMT) utilizes only monolingual data for training. The quality of back-translated data plays an important role in the performance of NMT systems. In back-translation, all generated pseudo parallel sentence pairs are not of the same quality. Taking inspiration from domain adaptation where in-domain sentences are given more weight in training, in this paper we propose an approach to filter back-translated data as part of the training process of unsupervised NMT. Our approach gives more weight to good pseudo parallel sentence pairs in the back-translation phase. We calculate the weight of each pseudo parallel sentence pair using sentence-wise round-trip BLEU score which is normalized batch-wise. We compare our approach with the current state of the art approaches for unsupervised NMT.

Filtering Back-Translated Data in Unsupervised Neural Machine Translation

Automatic Charge Identification (ACI) is the task of identifying the relevant legal charges given the facts of a situation and the statutory laws that define these charges, and is a crucial aspect of the judicial process. Prior works focus on learning charge-side representations by modeling relationships between the charges, but not much effort has been made in improving fact-side representations. We observe that only a small fraction of sentences in the facts actually indicates the charges. 
We show that by using a very small subset (3%) of fact descriptions annotated with sentence-level charges, we can achieve an improvement across a range of different ACI models, as compared to modeling just the main document-level task on a much larger dataset.
Additionally, we propose a novel model that utilizes sentence-level charge labels as an auxiliary task, coupled with the main task of document-level charge identification in a multi-task learning framework. The proposed model comprehensively outperforms a large number of recent baseline models for ACI. The improvement in performance is particularly noticeable for the rare charges which are known to be especially challenging to identify.

Automatic Charge Identification from Facts: A Few Sentence-Level Charge Annotations is All You Need

Self-Attention Networks (SANs) are an integral part of successful neural architectures such as Transformer (Vaswani et al., 2017), and thus of pretrained language models such as BERT (Devlin et al., 2019) or GPT-3 (Brown et al., 2020). Training SANs on a task or pretraining them on language modeling requires large amounts of data and compute resources. We are searching for modifications to SANs that enable faster learning, i.e., higher accuracies after fewer update steps. We investigate three modifications to SANs: direct position interactions, learnable temperature, and convoluted attention. When evaluating them on part-of-speech tagging, we find that direct position interactions are an alternative to position embeddings, and convoluted attention has the potential to speed up the learning process.

Downloads

Next from COLING 2020

Utilizing Subword Entitiesin Character-Level Sequence-to-Sequence Lemmatization Models

Similar lecture

How Relevant Are Selectional Preferences for Transformer-based Language Models?

.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 COLING 2020

Utilizing Subword Entitiesin Character-Level Sequence-to-Sequence Lemmatization Models

Similar lecture

How Relevant Are Selectional Preferences for Transformer-based Language Models?

Downloads