Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userMonitoring geometrical properties of word embeddings for detecting the emergence of new topics.
رصد الخصائص الهندسية ل Adgeddings Word للكشف عن ظهور مواضيع جديدة.
245
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
إن اكتشاف موضوع الناشئ البطيء هو مهمة بين اكتشاف الحدث، حيث نكمل السلوكيات من الكلمات المختلفة في فترة قصيرة من الزمن، وتطور اللغة، حيث نراقب تطورها الطويل الأجل.في هذا العمل، نتعامل مع مشكلة الكشف المبكر عن المواضيع الجديدة المبكرة.تحقيقا لهذه الغاية، نجمع أدلة على إشارات ضعيفة على مستوى الكلمة.نقترح مراقبة سلوك تمثيل الكلمات في مساحة تضمين واستخدام إحدى خصائصها الهندسية لتوصيف ظهور المواضيع.نظرا لأن التقييم يصعب عادة على هذا النوع من المهمة، فإننا نقدم إطارا للتقييم الكمي وإظهار النتائج الإيجابية التي تتفوق على الأساليب الحديثة من بين الفن.يتم تقييم طريقتنا على مجموعة بيانات عامة للصحافة والمقالات العلمية.
Slow emerging topic detection is a task between event detection, where we aggregate behaviors of different words on short period of time, and language evolution, where we monitor their long term evolution. In this work, we tackle the problem of early detection of slowly emerging new topics. To this end, we gather evidence of weak signals at the word level. We propose to monitor the behavior of words representation in an embedding space and use one of its geometrical properties to characterize the emergence of topics. As evaluation is typically hard for this kind of task, we present a framework for quantitative evaluation and show positive results that outperform state-of-the-art methods. Our method is evaluated on two public datasets of press and scientific articles.
References used
https://aclanthology.org/
rate research
Read More
We evaluate the use of direct intrinsic word embedding evaluation tasks for specialized language. Our case study is philosophical text: human expert judgements on the relatedness of philosophical terms are elicited using a synonym detection task and
a coherence task. Uniquely for our task, experts must rely on explicit knowledge and cannot use their linguistic intuition, which may differ from that of the philosopher. We find that inter-rater agreement rates are similar to those of more conventional semantic annotation tasks, suggesting that these tasks can be used to evaluate word embeddings of text types for which implicit knowledge may not suffice.
In writing, humor is mainly based on figurative language in which words and expressions change their conventional meaning to refer to something without saying it directly. This flip in the meaning of the words prevents Natural Language Processing fro
m revealing the real intention of a communication and, therefore, reduces the effectiveness of tasks such as Sentiment Analysis or Emotion Detection. In this manuscript we describe the participation of the UMUTeam in HaHackathon 2021, whose objective is to detect and rate humorous and controversial content. Our proposal is based on the combination of linguistic features with contextual and non-contextual word embeddings. We participate in all the proposed subtasks achieving our best result in the controversial humor subtask.
Generative adversarial networks (GANs) have succeeded in inducing cross-lingual word embeddings - maps of matching words across languages - without supervision. Despite these successes, GANs' performance for the difficult case of distant languages is
still not satisfactory. These limitations have been explained by GANs' incorrect assumption that source and target embedding spaces are related by a single linear mapping and are approximately isomorphic. We assume instead that, especially across distant languages, the mapping is only piece-wise linear, and propose a multi-adversarial learning method. This novel method induces the seed cross-lingual dictionary through multiple mappings, each induced to fit the mapping for one subspace. Our experiments on unsupervised bilingual lexicon induction and cross-lingual document classification show that this method improves performance over previous single-mapping methods, especially for distant languages.
Eye-tracking psycholinguistic studies have suggested that context-word semantic coherence and predictability influence language processing during the reading activity. In this study, we investigate the correlation between the cosine similarities comp
uted with word embedding models (both static and contextualized) and eye-tracking data from two naturalistic reading corpora. We also studied the correlations of surprisal scores computed with three state-of-the-art language models. Our results show strong correlation for the scores computed with BERT and GloVe, suggesting that similarity can play an important role in modeling reading times.
Growing polarization of the news media has been blamed for fanning disagreement, controversy and even violence. Early identification of polarized topics is thus an urgent matter that can help mitigate conflict. However, accurate measurement of topic-
wise polarization is still an open research challenge. To address this gap, we propose Partisanship-aware Contextualized Topic Embeddings (PaCTE), a method to automatically detect polarized topics from partisan news sources. Specifically, utilizing a language model that has been finetuned on recognizing partisanship of the news articles, we represent the ideology of a news corpus on a topic by corpus-contextualized topic embedding and measure the polarization using cosine distance. We apply our method to a dataset of news articles about the COVID-19 pandemic. Extensive experiments on different news sources and topics demonstrate the efficacy of our method to capture topical polarization, as indicated by its effectiveness of retrieving the most polarized topics.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
