Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userFine-grained Entity Typing via Label Reasoning
كيان غرامة الكتابة عن طريق تسمية التسمية
220
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تستند نهج كتابة الكيانات التقليدية إلى نماذج تصنيف مستقلة، مما يجعلها من الصعب التعرف على أنواع الكيان المعتمدة والذات طويل الذيل والحبوب. في هذه الورقة، نجادل بأن التبعيات الخارجية والمترنوية المتطودة ضمنيا بين الملصقات يمكن أن توفر معرفة حاسمة لمعالجة التحديات المذكورة أعلاه. تحقيقا لهذه الغاية، نقترح شبكة تسمية الملصقات (LRN)، والتي الأسباب التسلل تسميات الكيانات الجميلة من خلال اكتشاف واستغلال المعرفة التبعيات الملصقات المتاحة في البيانات. على وجه التحديد، تستخدم LRN شبكة التراجع التلقائي لإجراء منطق استنتاجي ورسم رسمي من السمة الحيوية لإجراء منطق حثي بين الملصقات، والتي يمكن أن تكفذ بشكل فعال، وتعلم وسبب تبعيات التسمية المعقدة في مجموعة تسلسل إلى مجموعة، ونهاية إلى نهاية وبعد تظهر التجارب أن LRN تحقق الأداء الحديثة على معايير كيانات كيانات فائقة الفيرلة القياسية، ويمكن أيضا حل مشكلة تسمية الذيل الطويل بشكل فعال.
Conventional entity typing approaches are based on independent classification paradigms, which make them difficult to recognize inter-dependent, long-tailed and fine-grained entity types. In this paper, we argue that the implicitly entailed extrinsic and intrinsic dependencies between labels can provide critical knowledge to tackle the above challenges. To this end, we propose Label Reasoning Network(LRN), which sequentially reasons fine-grained entity labels by discovering and exploiting label dependencies knowledge entailed in the data. Specifically, LRN utilizes an auto-regressive network to conduct deductive reasoning and a bipartite attribute graph to conduct inductive reasoning between labels, which can effectively model, learn and reason complex label dependencies in a sequence-to-set, end-to-end manner. Experiments show that LRN achieves the state-of-the-art performance on standard ultra fine-grained entity typing benchmarks, and can also resolve the long tail label problem effectively.
References used
https://aclanthology.org/
rate research
Read More
Existing work on Fine-grained Entity Typing (FET) typically trains automatic models on the datasets obtained by using Knowledge Bases (KB) as distant supervision. However, the reliance on KB means this training setting can be hampered by the lack of
or the incompleteness of the KB. To alleviate this limitation, we propose a novel setting for training FET models: FET without accessing any knowledge base. Under this setting, we propose a two-step framework to train FET models. In the first step, we automatically create pseudo data with fine-grained labels from a large unlabeled dataset. Then a neural network model is trained based on the pseudo data, either in an unsupervised way or using self-training under the weak guidance from a coarse-grained Named Entity Recognition (NER) model. Experimental results show that our method achieves competitive performance with respect to the models trained on the original KB-supervised datasets.
Analyzing microblogs where we post what we experience enables us to perform various applications such as social-trend analysis and entity recommendation. To track emerging trends in a variety of areas, we want to categorize information on emerging en
tities (e.g., Avatar 2) in microblog posts according to their types (e.g., Film). We thus introduce a new entity typing task that assigns a fine-grained type to each emerging entity when a burst of posts containing that entity is first observed in a microblog. The challenge is to perform typing from noisy microblog posts without relying on prior knowledge of the target entity. To tackle this task, we build large-scale Twitter datasets for English and Japanese using time-sensitive distant supervision. We then propose a modular neural typing model that encodes not only the entity and its contexts but also meta information in multiple posts. To type homographic' emerging entities (e.g., Go' means an emerging programming language and a classic board game), which contexts are noisy, we devise a context selector that finds related contexts of the target entity. Experiments on the Twitter datasets confirm the effectiveness of our typing model and the context selector.
The training of NLP models often requires large amounts of labelled training data, which makes it difficult to expand existing models to new languages. While zero-shot cross-lingual transfer relies on multilingual word embeddings to apply a model tra
ined on one language to another, Yarowski and Ngai (2001) propose the method of annotation projection to generate training data without manual annotation. This method was successfully used for the tasks of named entity recognition and coarse-grained entity typing, but we show that it is outperformed by zero-shot cross-lingual transfer when applied to the similar task of fine-grained entity typing. In our study of fine-grained entity typing with the FIGER type ontology for German, we show that annotation projection amplifies the English model's tendency to underpredict level 2 labels and is beaten by zero-shot cross-lingual transfer on three novel test sets.
Despite the success of neural dialogue systems in achieving high performance on the leader-board, they cannot meet users' requirements in practice, due to their poor reasoning skills. The underlying reason is that most neural dialogue models only cap
ture the syntactic and semantic information, but fail to model the logical consistency between the dialogue history and the generated response. Recently, a new multi-turn dialogue reasoning task has been proposed, to facilitate dialogue reasoning research. However, this task is challenging, because there are only slight differences between the illogical response and the dialogue history. How to effectively solve this challenge is still worth exploring. This paper proposes a Fine-grained Comparison Model (FCM) to tackle this problem. Inspired by human's behavior in reading comprehension, a comparison mechanism is proposed to focus on the fine-grained differences in the representation of each response candidate. Specifically, each candidate representation is compared with the whole history to obtain a history consistency representation. Furthermore, the consistency signals between each candidate and the speaker's own history are considered to drive a model prefer a candidate that is logically consistent with the speaker's history logic. Finally, the above consistency representations are employed to output a ranking list of the candidate responses for multi-turn dialogue reasoning. Experimental results on two public dialogue datasets show that our method obtains higher ranking scores than the baseline models.
Supervised learning assumes that a ground truth label exists. However, the reliability of this ground truth depends on human annotators, who often disagree. Prior work has shown that this disagreement can be helpful in training models. We propose a n
ovel method to incorporate this disagreement as information: in addition to the standard error computation, we use soft-labels (i.e., probability distributions over the annotator labels) as an auxiliary task in a multi-task neural network. We measure the divergence between the predictions and the target soft-labels with several loss-functions and evaluate the models on various NLP tasks. We find that the soft-label prediction auxiliary task reduces the penalty for errors on ambiguous entities, and thereby mitigates overfitting. It significantly improves performance across tasks, beyond the standard approach and prior work.
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
