Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDoes syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa
هل تامة بناء الجملة؟خط أساس قوي لتحليل المعنويات القائم على الجانب مع روبرتا
254
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تحليل المعنويات المستندة إلى جانب الجسيم (ABASA)، تهدف إلى التنبؤ بأقطاب الجوانب، هي مهمة جيدة المحبوس في مجال تحليل المعنويات. وأظهر العمل السابق معلومات النحوية، على سبيل المثال أشجار التبعية، يمكن أن تحسن بشكل فعال أداء ABSA. في الآونة الأخيرة، أظهرت النماذج المدربة مسبقا (PTMS) أيضا فعاليتها على ABAMA. لذلك، تنشأ السؤال بشكل طبيعي ما إذا كانت PTMs تحتوي على معلومات نصنية كافية ل ABAMA حتى نتمكن من الحصول على نموذج ABSA جيد فقط بناء على PTMS. في هذه الورقة، نقارن أولا الأشجار المستحثة من PTMS وأشجار تحليل التبعية في العديد من النماذج الشعبية لمهمة ABASA، والتي توضح أن الشجرة المستحقة من روبرتا الصعبة (FT-Roberta) تتفوق على الشجرة التي قدمتها المحلل المحاور. تكشف تجارب التحليل الإضافي أن شجرة FT-Roberta المستحقة أكثر من المعنويات - الموجهة إلى كلمة ويمكن أن تفيد مهمة ABASA. تشير التجارب أيضا إلى أن النموذج النقي المستند إلى روبرتا يمكن أن تفوق أو تقريب من عروض SOTA السابقة على ست مجموعات بيانات عبر أربع لغات لأنها تتضمن ضمنيا المعلومات الأساسية الموجهة نحو المهام.
Aspect-based Sentiment Analysis (ABSA), aiming at predicting the polarities for aspects, is a fine-grained task in the field of sentiment analysis. Previous work showed syntactic information, e.g. dependency trees, can effectively improve the ABSA performance. Recently, pre-trained models (PTMs) also have shown their effectiveness on ABSA. Therefore, the question naturally arises whether PTMs contain sufficient syntactic information for ABSA so that we can obtain a good ABSA model only based on PTMs. In this paper, we firstly compare the induced trees from PTMs and the dependency parsing trees on several popular models for the ABSA task, showing that the induced tree from fine-tuned RoBERTa (FT-RoBERTa) outperforms the parser-provided tree. The further analysis experiments reveal that the FT-RoBERTa Induced Tree is more sentiment-word-oriented and could benefit the ABSA task. The experiments also show that the pure RoBERTa-based model can outperform or approximate to the previous SOTA performances on six datasets across four languages since it implicitly incorporates the task-oriented syntactic information.
References used
https://aclanthology.org/
rate research
Read More
Both the issues of data deficiencies and semantic consistency are important for data augmentation. Most of previous methods address the first issue, but ignore the second one. In the cases of aspect-based sentiment analysis, violation of the above is
sues may change the aspect and sentiment polarity. In this paper, we propose a semantics-preservation data augmentation approach by considering the importance of each word in a textual sequence according to the related aspects and sentiments. We then substitute the unimportant tokens with two replacement strategies without altering the aspect-level polarity. Our approach is evaluated on several publicly available sentiment analysis datasets and the real-world stock price/risk movement prediction scenarios. Experimental results show that our methodology achieves better performances in all datasets.
In cross-lingual Abstract Meaning Representation (AMR) parsing, researchers develop models that project sentences from various languages onto their AMRs to capture their essential semantic structures: given a sentence in any language, we aim to captu
re its core semantic content through concepts connected by manifold types of semantic relations. Methods typically leverage large silver training data to learn a single model that is able to project non-English sentences to AMRs. However, we find that a simple baseline tends to be overlooked: translating the sentences to English and projecting their AMR with a monolingual AMR parser (translate+parse,T+P). In this paper, we revisit this simple two-step base-line, and enhance it with a strong NMT system and a strong AMR parser. Our experiments show that T+P outperforms a recent state-of-the-art system across all tested languages: German, Italian, Spanish and Mandarin with +14.6, +12.6, +14.3 and +16.0 Smatch points
Aspect-based sentiment analysis (ABSA) mainly involves three subtasks: aspect term extraction, opinion term extraction, and aspect-level sentiment classification, which are typically handled in a separate or joint manner. However, previous approaches
do not well exploit the interactive relations among three subtasks and do not pertinently leverage the easily available document-level labeled domain/sentiment knowledge, which restricts their performances. To address these issues, we propose a novel Iterative Multi-Knowledge Transfer Network (IMKTN) for end-to-end ABSA. For one thing, through the interactive correlations between the ABSA subtasks, our IMKTN transfers the task-specific knowledge from any two of the three subtasks to another one at the token level by utilizing a well-designed routing algorithm, that is, any two of the three subtasks will help the third one. For another, our IMKTN pertinently transfers the document-level knowledge, i.e., domain-specific and sentiment-related knowledge, to the aspect-level subtasks to further enhance the corresponding performance. Experimental results on three benchmark datasets demonstrate the effectiveness and superiority of our approach.
Aspect-based sentiment analysis (ABSA) typically focuses on extracting aspects and predicting their sentiments on individual sentences such as customer reviews. Recently, another kind of opinion sharing platform, namely question answering (QA) forum,
has received increasing popularity, which accumulates a large number of user opinions towards various aspects. This motivates us to investigate the task of ABSA on QA forums (ABSA-QA), aiming to jointly detect the discussed aspects and their sentiment polarities for a given QA pair. Unlike review sentences, a QA pair is composed of two parallel sentences, which requires interaction modeling to align the aspect mentioned in the question and the associated opinion clues in the answer. To this end, we propose a model with a specific design of cross-sentence aspect-opinion interaction modeling to address this task. The proposed method is evaluated on three real-world datasets and the results show that our model outperforms several strong baselines adopted from related state-of-the-art models.
Aspect-level sentiment classification (ALSC) aims at identifying the sentiment polarity of a specified aspect in a sentence. ALSC is a practical setting in aspect-based sentiment analysis due to no opinion term labeling needed, but it fails to interp
ret why a sentiment polarity is derived for the aspect. To address this problem, recent works fine-tune pre-trained Transformer encoders for ALSC to extract an aspect-centric dependency tree that can locate the opinion words. However, the induced opinion words only provide an intuitive cue far below human-level interpretability. Besides, the pre-trained encoder tends to internalize an aspect's intrinsic sentiment, causing sentiment bias and thus affecting model performance. In this paper, we propose a span-based anti-bias aspect representation learning framework. It first eliminates the sentiment bias in the aspect embedding by adversarial learning against aspects' prior sentiment. Then, it aligns the distilled opinion candidates with the aspect by span-based dependency modeling to highlight the interpretable opinion terms. Our method achieves new state-of-the-art performance on five benchmarks, with the capability of unsupervised opinion extraction.
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
