Related papers: Exploiting Duality in Open Information Extraction …
Tagging based relational triple extraction methods are attracting growing research attention recently. However, most of these methods take a unidirectional extraction framework that first extracts all subjects and then extracts objects and…
Pre-trained large language models can perform natural language processing downstream tasks by conditioning on human-designed prompts. However, a prompt-based approach often requires "prompt engineering" to design different prompts,…
An extractive rationale explains a language model's (LM's) prediction on a given task instance by highlighting the text inputs that most influenced the prediction. Ideally, rationale extraction should be faithful (reflective of LM's actual…
Information extraction(IE) has always been one of the essential tasks of NLP. Moreover, one of the most critical application scenarios of information extraction is the information extraction of resumes. Constructed text is obtained by…
Large Language Models (LLMs) are often used as automated judges to evaluate text, but their effectiveness can be hindered by various unintentional biases. We propose using linear classifying probes, trained by leveraging differences between…
Obtaining an explicit understanding of communication within a Hybrid Intelligence collaboration is essential to create controllable and transparent agents. In this paper, we describe a number of Natural Language Understanding models that…
Recent advancements in large language models have shown impressive performance in general chat. However, their domain-specific capabilities, particularly in information extraction, have certain limitations. Extracting structured information…
Event extraction (EE), which acquires structural event knowledge from texts, can be divided into two sub-tasks: event type classification and element extraction (namely identifying triggers and arguments under different role patterns). As…
Synthesis of digital artifacts conditioned on user prompts has become an important paradigm facilitating an explosion of use cases with generative AI. However, such models often fail to connect the generated outputs and desired target…
With rise of digital age, there is an explosion of information in the form of news, articles, social media, and so on. Much of this data lies in unstructured form and manually managing and effectively making use of it is tedious, boring and…
Zero-shot cross-lingual information extraction (IE) describes the construction of an IE model for some target language, given existing annotations exclusively in some other language, typically English. While the advance of pretrained…
Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in reasoning tasks. While scaling rollouts can stabilize training and enhance performance, the computational overhead is a critical issue. In…
We build a reference for the task of Open Information Extraction, on five documents. We tentatively resolve a number of issues that arise, including inference and granularity. We seek to better pinpoint the requirements for the task. We…
We present data augmentation techniques for process extraction tasks in scientific publications. We cast the process extraction task as a sequence labeling task where we identify all the entities in a sentence and label them according to…
While Large Language Models (LLMs) demonstrate impressive reasoning capabilities, understanding and validating their knowledge utilization remains challenging. Chain-of-thought (CoT) prompting partially addresses this by revealing…
We present a study on leveraging multilingual pre-trained generative language models for zero-shot cross-lingual event argument extraction (EAE). By formulating EAE as a language generation task, our method effectively encodes event…
Span-level emotion-cause-category triplet extraction represents a novel and complex challenge within emotion cause analysis. This task involves identifying emotion spans, cause spans, and their associated emotion categories within the text…
Structured knowledge bases (KBs) are the backbone of many know\-ledge-intensive applications, and their automated construction has received considerable attention. In particular, open information extraction (OpenIE) is often used to induce…
In knowledge graph construction, a challenging issue is how to extract complex (e.g., overlapping) entities and relationships from a small amount of unstructured historical data. The traditional pipeline methods are to divide the extraction…
Generative models have recently started to outperform extractive models in Open Domain Question Answering, largely by leveraging their decoder to attend over multiple encoded passages and combining their information. However, generative…