Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
We introduce a general, interest-aware topic model (IATM), in which known higher-level interests on topics expressed by each user can be modeled. We then specialize the IATM for use in consumer health forum thread recommendation by... more
We introduce a general, interest-aware topic model (IATM), in which known higher-level interests on topics expressed by each user can be modeled. We then specialize the IATM for use in consumer health forum thread recommendation by equating each user's self-reported medical conditions as interests and topics as symptoms of treatments for recommendation. The IATM additionally models the implicit interests embodied by users' textual descriptions in their profiles. To further enhance the personalized nature of the recommendations, we introduce jointly normalized collaborative topic regression (JNCTR) which captures how users interact with the various symptoms belonging to the same clinical condition. In our experiments on two real-world consumer health forums, our proposed model significantly outperforms competitive state-of-the-art baselines by over 10% in recall. Importantly, we show that our IATM+JNCTR pipeline also imbues the recommendation process with added transparency, allowing a recommendation system to justify its recommendation with respect to each user's interest in certain health conditions.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
This chapter examines the techniques behind a user interface that computes a multi-document summary of documents retrieved by a search. As a user’s query can retrieve thousands of relevant documents, it is paramount that they be logically... more
This chapter examines the techniques behind a user interface that computes a multi-document summary of documents retrieved by a search. As a user’s query can retrieve thousands of relevant documents, it is paramount that they be logically organized. In digital libraries, documents are traditionally represented as a ranked list of documents ordered by computed relevance and do not take into account presentation techniques used by information professionals (such as librarians) in the physical library. This chapter examines a framework used in a consumer healthcare digital library that incorporates techniques used by librarians. It brings together commonalities between documents and highlights their salient differences to target the needs of users using the browsing and searching modes of information seeking. It achieves this by discovering common and unique topics among its input from a combination of structural and lexical cues.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
The robustness of pretrained language models(PLMs) is generally measured using performance drops on two or more domains. However, we do not yet understand the inherent robustness achieved by contributions from different layers of a PLM.... more
The robustness of pretrained language models(PLMs) is generally measured using performance drops on two or more domains. However, we do not yet understand the inherent robustness achieved by contributions from different layers of a PLM. We systematically analyze the robustness of these representations layer by layer from two perspectives. First, we measure the robustness of representations by using domain divergence between two domains. We find that i) Domain variance increases from the lower to the upper layers for vanilla PLMs; ii) Models continuously pretrained on domain-specific data (DAPT)(Gururangan et al., 2020) exhibit more variance than their pretrained PLM counterparts; and that iii) Distilled models (e.g., DistilBERT) also show greater domain variance. Second, we investigate the robustness of representations by analyzing the encoded syntactic and semantic information using diagnostic probes. We find that similar layers have similar amounts of linguistic information for da...