Spain

This poster describes the method developed for the Task 2 English variation of the Social Media Mining for Health Applications (SMM4H) 2020 shared task. The task was to classify tweets containing adverse effects (AE) after medication intake. Our approach combined transfer learning using a RoBERTa Large Transformer model with a rule-based post-prediction correction to improve model precision. The model’s F1-Score of 0.56 on the test dataset was 10% better than the mean of the F1-Score of the best submissions in the task.

COLING 2020

RoBERTa and Rules Adverse drug reaction detection in Twitter

adverse drug reactions

social media mining

deep learning

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

This paper describes our submission to the 5th edition of the Social Media Mining for Health Applications (SMM4H) shared task 1. Task 1 aims at the automatic classification of tweets that mention a medication or a dietary supplement. This task is specifically challenging due to its highly imbalanced dataset, with only 0.2% of the tweets mentioning a drug. For our submission, we particularly focused on several pretrained encoders for text classification. We achieve an F1 score of 0.75 for the positive class on the test set.

pre-trained sentence encoders

This work describes our participation in the Social Media Mining for Health Application(SMM4H 2020) Challenge Track 2 for identifying tweets containing Adverse Effects (AEs). Our system uses Convolutional Neural Networks. We explore downsampling, oversampling, and adjusting the class weights to account for the imbalanced nature of the dataset. Our results showed downsampling outperformed oversampling and adjusting the class weights on the test set however all three obtained similar results on the development set.

Identifying adverse effects in English tweets for unbalanced data

This paper describes our approach for detecting adverse drug effect mentions on Twitter as part of the Social Media Mining for Health Applications (SMM4H) 2020, Shared Task 2. Our approach utilizes multilingual sentence embeddings (sentence-BERT) for representing tweets and Bayesian hyperparameter optimization of sample weighting parameter for counterbalancing high class imbalance.

Sentence Transformers and Bayesian Optimization for Adverse Drug Effect Detection from Twitter

We detect birth defect mentions in tweets using specialized gazetteers and syntactic dependency relations in a multi-layer transformer architecture with attention.

Birth defect mention detection

Textual definitions constitute a fundamental source of knowledge when seeking the meaning of words, and they are the cornerstone of lexical resources like glossaries, dictionaries, encyclopedia or thesauri. In this paper, we present an in-depth analytical study on the main features relevant to the task of definition extraction. Our main goal is to study whether linguistic structures from canonical (the Aristotelian or genus et differentia model) can be leveraged to retrieve
definitions from corpora in different domains of knowledge and textual genres alike. To this end, we develop a simple linear classifier and analyze the contribution of several (sets of) linguistic features. Finally, as a result of our experiments, we also shed light on the particularities of existing benchmarks as well as the most challenging aspects of the task.

Definition Extraction Feature Analysis:From Canonical to Naturally-Occurring Definitions


Speech disfluencies have been hypothesized to occur before words that are less predictable and therefore more cognitively demanding. In this paper, we revisit this hypothesis by using OpenAI's GPT-2 to calculate predictability of words as language model perplexity. Using the Switchboard corpus, we find that 51% of disfluencies occur at the highest, second highest, or within one token of the highest perplexity, and this distribution is not random. We also show that disfluencies precede words with significantly higher perplexity than fluent contexts. Based on our results, we offer new evidence that disfluencies are more likely to occur before less predictable words.

Speech Disfluencies occur at Higher Perplexities

Language transfer can facilitate learning L2 words whose form and meaning are similar to L1 words, or hinder speakers when the languages differ. L2 idioms introduce another layer of challenge, as language transfer could occur on the literal or figurative level of meaning. Thus, the mechanics of language transfer for idiom processing shed light on how literal and figurative meaning is stored in the bilingual lexicon. Three factors appear to influence how language transfer affects idiom comprehension: bilingual fluency, processing of literal-figurative vs. figurative cognate idioms (idioms with the same wording and meaning in both languages, or the same meaning only), and comprehension of literal vs. figurative meaning of a given idiom. To examine the relationship between these factors, this study investigated English-Spanish bilinguals’ reaction time on a lexical decision task examining literal-figurative and figurative cognate idioms. The results suggest that fluency increases processing speed rather than slow it down due to language transfer, and that language transfer from L1 to L2 occurs on the level of figurative meaning in L1-dominant bilinguals.

Bilingual Lexical Access and Cognate Idiom Comprehension

We report ongoing research on linking elements in German compounds, with a focus on noun-noun compounds in which the first constituent is ending in schwa. We present a corpus of about 3000 nouns ending in schwa, annotated for various phonological and morpho-syntactic features, and critically, the dominant linking strategy. The corpus analysis is complemented by an unsuccessful attempt to train neural networks and by a pilot experiment asking native speakers to indicate their preferred linking strategy for nonce words. While neither the corpus study nor the experiment offer a clear picture, the results nevertheless provide interesting insights into the intricacies of German compounding. Overall, we find a predominance of the paradigmatic linking element -n. At the same time, the results show that -n is not a default strategy.

Schwa-deletion in German noun-noun compounds

Existing dictionaries may help collocation translation by suggesting associated words in the form of collocations, thesaurus, and example sentences. We propose to enhance them with task-driven word associations, illustrating the need by a few scenarios and outlining a possible approach based on word embedding. An example is given, using pre-trained word embedding, while more extensive investigation with more refined methods and resources is underway.

Translating Collocations: The Need for Task-driven Word Associations

The HSemID system, submitted to the CogALex VI Shared Task is a hybrid system relying mainly on metric clusters measured in large web corpora, complemented by a vector space model using cosine similarity to detect semantic associations. Although the system reached ra-ther weak results for the subcategories of synonyms, antonyms and hypernyms, with some dif-ferences from one language to another, it is able to measure general semantic associations (as being random or not-random) with an F1 score close to 0.80. The results strongly suggest that idiomatic constructions play a fundamental role in semantic associations. Further experiments are necessary in order to fine-tune the model to the subcategories of synonyms, antonyms, hy-pernyms and to explain surprising differences across languages.

Downloads

Next from COLING 2020

pre-trained sentence encoders

Similar lecture

pre-trained sentence encoders

.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

pre-trained sentence encoders

Similar lecture

pre-trained sentence encoders

Downloads