Entity Linking in 100 Languages

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 7833–7845, November 16–20, 2020. c⃝2020 Association for Computational Linguistics 7833 Entity Linking in 100 Languages Jan A. Botha Google Research jabot@google.com Zifei Shan Google Research zifeishan@gmail.com Daniel Gillick Google Research dgillick@google.com Abstract We propose a new formulation for multilingual entity linking, where language-specific men- tions resolve to a language-agnostic Knowl- edge Base. We train a dual encoder in this new setting, building on prior work with improved feature representation, negative mining, and an auxiliary entity-pairing task, to obtain a sin- gle entity retrieval model that covers 100+ lan- guages and 20 million entities. The model outperforms state-of-the-art results from a far more limited cross-lingual linking task. Rare entities and low-resource languages pose chal- lenges at this large-scale, so we advocate for an increased focus on zero- and few-shot eval- uation. To this end, we provide Mewsli-9, a large new multilingual dataset1 matched to our setting, and show how frequency-based anal- ysis provided key insights for our model and training enhancements. 1 Introduction Entity linking (EL) fulfils a key role in grounded language understanding: Given an ungrounded en- tity mention in text, the task is to identify the en- tity’s corresponding entry in a Knowledge Base (KB). In particular, EL provides grounding for ap- plications like Question Answering (Févry et al., 2020b) (also via Semantic Parsing (Shaw et al., 2019)) and Text Generation (Puduppully et al., 2019); it is also an essential component in knowl- edge base population (Shen et al., 2014). Entities have played a growing role in representation learn- ing. For example, entity mention masking led to greatly improved fact retention in large language models (Guu et al., 2020; Roberts et al., 2020). But to date, the primary formulation of EL out- side of the standard monolingual setting has been cross-lingual: link mentions expressed in one lan- guage to a KB expressed in another (McNamee et al., 2011; Tsai and Roth, 2016; Sil et al., 2018). 1http://goo.gle/mewsli-dataset The accompanying motivation is that KBs may only ever exist in some well-resourced languages, but that text in many different languages need to be linked. Recent work in this direction features progress on low-resource languages (Zhou et al., 2020), zero-shot transfer (Sil and Florian, 2016; Ri- jhwani et al., 2019; Zhou et al., 2019) and scaling to many languages (Pan et al., 2017), but commonly assumes a single primary KB language and a lim- ited KB, typically English Wikipedia. We contend that this popular formulation lim- its the scope of EL in ways that are artificial and inequitable. First, it artificially simplifies the task by restrict- ing the set of viable entities and reducing the va- riety of mention ambiguities. Limiting the focus to entities that have English Wikipedia pages un- derstates the real-world diversity of entities. Even within the Wikipedia ecosystem, many entities only have pages in languages other than English. These are often associated with locales that are already underrepresented on the global stage. By ignoring these …

Content truncated to 500 words