Aspect Sentiment Triplet Extraction (ASTE) is a challenging task in sentiment analysis, aiming to provide fine-grained insights into human sentiments. However, existing benchmarks are limited to two domains and do not evaluate model performance on unseen domains, raising concerns about the generalization of proposed methods. Furthermore, it remains unclear if large language models (LLMs) can effectively handle complex sentiment tasks like ASTE. In this work, we address the issue of generalization in ASTE from both a benchmarking and modeling perspective. We introduce a domain-expanded benchmark by annotating samples from diverse domains, enabling evaluation of models in both in-domain and out-of-domain settings. Additionally, we propose CASE, a simple and effective decoding strategy that enhances trustworthiness and performance of LLMs in ASTE. Through comprehensive experiments involving multiple tasks, settings, and models, we demonstrate that CASE can serve as a general decoding strategy for complex sentiment tasks. By expanding the scope of evaluation and providing a more reliable decoding strategy, we aim to inspire the research community to reevaluate the generalizability of benchmarks and models for ASTE. Our code, data, and models are available at https://github.com/DAMO-NLP-SG/domain-expanded-aste.

The DocRED dataset is one of the most popular and widely used benchmarks for document-level relation extraction (RE). It adopts a recommend-revise annotation scheme so as to have a large-scale annotated dataset. However, we find that the annotation of DocRED is incomplete, i.e., false negative samples are prevalent. We analyze the causes and effects of the overwhelming false negative problem in the DocRED dataset. To address the shortcoming, we re-annotate 4,053 documents in the DocRED dataset by adding the missed relation triples back to the original DocRED. We name our revised DocRED dataset Re-DocRED. We conduct extensive experiments with state-of-the-art neural models on both datasets, and the experimental results show that the models trained and evaluated on our Re-DocRED achieve performance improvements of around 13 F1 points. Moreover, we conduct a comprehensive analysis to identify the potential areas for further improvement.

Relation extraction has the potential for large-scale knowledge graph construction, but current methods do not consider the qualifier attributes for each relation triplet, such as time, quantity or location. The qualifiers form hyper-relational facts which better capture the rich and complex knowledge graph structure. For example, the relation triplet (Leonard Parker, Educated At, Harvard University) can be factually enriched by including the qualifier (End Time, 1967). Hence, we propose the task of hyper-relational extraction to extract more specific and complete facts from text. To support the task, we construct HyperRED, a large-scale and general-purpose dataset. Existing models cannot perform hyper-relational extraction as it requires a model to consider the interaction between three entities. Hence, we propose CubeRE, a cube-filling model inspired by table-filling approaches and explicitly considers the interaction between relation triplets and qualifiers. To improve model scalability and reduce negative class imbalance, we further propose a cube-pruning method. Our experiments show that CubeRE outperforms strong baselines and reveal possible directions for future research. Our code and data are available at github.com/declare-lab/HyperRED.

Exploiting sentence-level labels, which are easy to obtain, is one of the plausible methods to improve low-resource named entity recognition (NER), where token-level labels are costly to annotate. Current models for jointly learning sentence and token labeling are limited to binary classification. We present a joint model that supports multi-class classification and introduce a simple variant of self-attention that allows the model to learn scaling factors. Our model produces 3.78%, 4.20%, 2.08% improvements in F1 over the BiLSTM-CRF baseline on e-commerce product titles in three different low-resource languages: Vietnamese, Thai, and Indonesian, respectively.

This paper discusses a Thai corpus, TaLAPi, fully annotated with word segmentation (WS), part-of-speech (POS) and named entity (NE) information with the aim to provide a high-quality and sufficiently large corpus for real-life implementation of Thai language processing tools. The corpus contains 2,720 articles (1,043,471words) from the entertainment and lifestyle (NE&L) domain and 5,489 articles (3,181,487 words) in the news (NEWS) domain, with a total of 35 POS tags and 10 named entity categories. In particular, we present an approach to segment and tag foreign and loan words expressed in transliterated or original form in Thai text corpora. We see this as an area for study as adapted and un-adapted foreign language sequences have not been well addressed in the literature and this poses a challenge to the annotation process due to the increasing use and adoption of foreign words in the Thai language nowadays. To reduce the ambiguities in POS tagging and to provide rich information for facilitating Thai syntactic analysis, we adapted the POS tags used in ORCHID and propose a framework to tag Thai text and also addresses the tagging of loan and foreign words based on the proposed segmentation strategy. TaLAPi also includes a detailed guideline for tagging the 10 named entity categories