Table 2.

Performance of different ADS-sds^a systems implemented by using all types of features or by dropping each individual type of feature, under 4 conditions using 100, 200, 500, and 1000 target-domain training examples^b.

ADS-sds system		AUC-ROCc				Average precision
		100	200	500	1000	100	200	500	1000
ADS-sds-ALLd		0.751	0.759	0.775	0.786	0.819	0.826	0.838	0.847
ADS-sds-woWEe		0.711	0.718	0.726	0.733	0.780	0.785	0.793	0.799
ADS-sds-woWE vs ADS-sds-ALL
	t99	30.37	32.74	59.92	112.25	36.61	39.63	81.04	124.15
	P value	<.001	<.001	<.001	<.001	<.001	<.001	<.001	<.001
ADS-sds-woSemf		0.753	0.760	0.772	0.782	0.823	0.829	0.838	0.845
ADS-sds-woSem vs ADS-sds-ALL
	t99			4.63	12.28	3.18	4.00		4.55
	P value			<.001	<.001	.002	<.001		<.001
ADS-sds-woATRg		0.751	0.759	0.774	0.786	0.819	0.826	0.838	0.847
ADS-sds-woGTFh		0.740	0.749	0.765	0.777	0.813	0.821	0.833	0.842
ADS-sds-woGTF vs ADS-sds-ALL
	t99	13.04	9.50	14.85	22.55	8.12	6.49	11.52	23.07
	P value	<.001	<.001	<.001	<.001	<.001	<.001	<.001	<.001
ADS-sds-woTLi		0.741	0.751	0.767	0.778	0.807	0.815	0.829	0.838
ADS-sds-woTL vs ADS-sds-ALL
	t99	11.21	10.81	19.78	25.58	16.43	17.15	34.50	41.72
	P value	<.001	<.001	<.001	<.001	<.001	<.001	<.001	<.001

^aADS-sds: adapted distant supervision-supervised distant supervision.

^bWe report the P values (if the P value ≤.05) and the corresponding t₉₉ values for differences between each implementation and ADS-sds-ALL.

^cAUC-ROC: area under the receiver operating characteristic curve.

^dADS-sds-ALL: ADS-sds with all types of features.

^eADS-sds-woWE: ADS-sds without word embedding.

^fADS-sds-woSem: ADS-sds without semantic features.

^gADS-sds-woATR: ADS-sds without features derived from automatic term recognition.

^hADS-sds-woGTF: ADS-sds without general-domain term frequency.

ⁱADS-sds-woTL: ADS-sds without term length.