Hinrich Schütze, Yatin Chaudhary, Pankaj Gupta
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Though word embeddings and topics are complementary representations, several past works have only used pretrained word embeddings in (neural) topic modeling to address data sparsity in short-text or small collection of documents. This work presents a novel neural topic modeling framework using multi-view embedding spaces: (1) pretrained topic-embeddings, and (2) pretrained word-embeddings (contextinsensitive from Glove and context-sensitive from BERT models) jointly from one or many sources to improve topic quality and better deal with polysemy. In doing so, we first build respective pools of pretrained topic (i.e., TopicPool) and word embeddings (i.e., WordPool). We then identify one or more relevant source domain(s) and transfer knowledge to guide meaningful learning in the sparse target domain. Within neural topic modeling, we quantify the quality of topics and document representations via generalization (perplexity), interpretability (topic coherence) and information retrieval (IR) using short-text, long-text, small and large document collections from news and medical domains. Introducing the multi-source multi-view embedding spaces, we have shown state-of-the-art neural topic modeling using 6 source (highresource) and 5 target (low-resource) corpora. Topic Topic Words Topic Label Z 1 (S 1 ) profit, growth, stocks, apple, fall, Trading consumer, buy, billion, shares Z 2 (S 2 ) smartphone, ipad, apple, app, Product Line iphone, devices, phone, tablet Z 3 (S 3 ) microsoft, mac, linux, ibm, ios, Operating System apple, xp, windows, software Z 4 (T ) apple, talk, computers, shares, ? disease, driver, electronics, profit, ios
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2104.08551")
get_code_for_paper("2104.08551")
have("2104.08551")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2104.08551.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2104.08551)
Connect an agent — have() is free.